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.
HTML result view exported from: https://openbenchmarking.org/result/2410047-NE-2309026NE47&grs&sro .
m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution System Layer m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 AMD Ryzen 9 7940HS @ 4.00GHz (8 Cores / 16 Threads) Win element M600 (SR500P03_P5C2V07 BIOS) AMD Device 14e8 80GB Western Digital WD_BLACK SN850X 2000GB AMD Phoenix1 16GB AMD Rembrandt Radeon HD Audio DELL S3422DW 2 x Realtek RTL8125 2.5GbE + Intel Wi-Fi 6 AX200 EndeavourOS rolling 6.4.12-arch1-1 (x86_64) Xfce 4.18 X Server 1.21.1.8 4.6 Mesa 23.1.6-arch1.4 (LLVM 16.0.6 DRM 3.52) GCC 13.2.1 20230801 ext4 3440x1440 AMD Ryzen 9 7940HS (14 Cores) QEMU Standard PC (Q35 + ICH9 2009) (4.2023.08-4 BIOS) Intel 82G33/G31/P35/P31 + ICH9 60GB Western Digital WD_BLACK SN850X 2000GB + 34GB QEMU HDD AMD Radeon 780M 16GB (2799/2800MHz) Intel 82801I Red Hat Virtio device 6.11.1-arch1-1 (x86_64) X Server 1.21.1.13 4.6 Mesa 24.2.3-arch1.1 (LLVM 18.1.8 DRM 3.58) GCC 14.2.1 20240910 + Clang 18.1.8 + LLVM 18.1.8 KVM OpenBenchmarking.org Kernel Details - Transparent Huge Pages: always Compiler 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: 0xa704101 Graphics 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-001 Python 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 3.12.6 Security 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 numenta-nab: Relative Entropy onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU numenta-nab: Windowed Gaussian scikit-learn: Sparsify onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPU numenta-nab: Contextual Anomaly Detector OSE ncnn: Vulkan GPU - resnet50 scikit-learn: Isotonic / Logistic onednn: IP Shapes 1D - f32 - CPU numenta-nab: Earthgecko Skyline ncnn: CPU - shufflenet-v2 ncnn: Vulkan GPU - vision_transformer onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU ncnn: CPU - vision_transformer ncnn: CPU - FastestDet numenta-nab: KNN CAD ncnn: Vulkan GPU - shufflenet-v2 onednn: Recurrent Neural Network Training - f32 - CPU ncnn: CPU - alexnet onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU ncnn: Vulkan GPU - FastestDet onednn: Recurrent Neural Network Training - u8s8f32 - CPU ncnn: Vulkan GPU - mnasnet onednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPU tensorflow-lite: Mobilenet Quant ncnn: Vulkan GPU - yolov4-tiny onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU ncnn: CPU - efficientnet-b0 ncnn: Vulkan GPU - mobilenet ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - regnety_400m onednn: Recurrent Neural Network Inference - f32 - CPU ncnn: Vulkan GPU - regnety_400m scikit-learn: Hist Gradient Boosting onednn: Convolution Batch Shapes Auto - f32 - CPU ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 onednn: IP Shapes 1D - bf16bf16bf16 - CPU ncnn: Vulkan GPU - squeezenet_ssd onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU ncnn: Vulkan GPU - alexnet scikit-learn: TSNE MNIST Dataset ncnn: CPU - vgg16 ncnn: Vulkan GPU - vgg16 tensorflow-lite: SqueezeNet onednn: IP Shapes 3D - f32 - CPU scikit-learn: Tree scikit-learn: SGDOneClassSVM tensorflow-lite: Inception V4 rnnoise: tensorflow-lite: Mobilenet Float numpy: scikit-learn: Plot Fast KMeans onednn: IP Shapes 3D - bf16bf16bf16 - CPU deepspeech: CPU scikit-learn: MNIST Dataset onednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPU numenta-nab: Bayesian Changepoint scikit-learn: SGD Regression onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU scikit-learn: Plot Ward scikit-learn: GLM scikit-learn: Lasso tensorflow-lite: NASNet Mobile tensorflow-lite: Inception ResNet V2 scikit-learn: Plot Hierarchical scikit-learn: Feature Expansions scikit-learn: Plot OMP vs. LARS ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - googlenet ncnn: CPU - squeezenet_ssd ncnn: CPU - yolov4-tiny ncnn: CPU - resnet50 ncnn: CPU - resnet18 ncnn: CPU - googlenet ncnn: CPU - blazeface ncnn: CPU - mnasnet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU - mobilenet onednn: Deconvolution Batch shapes_3d - f32 - CPU shoc: OpenCL - S3D m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 9.716 1.07871 6.466 104.148 2.75936 30.663 10.37 1118.014 4.54620 86.570 1.97 54.04 0.912151 53.79 2.49 107.122 2.01 2672.08 4.52 1402.63 2714.85 2.48 2718.50 2.21 8.55150 3105.79 13.60 1409.84 1.58351 3.30 8.24 2.23 5.14 1436.72 5.22 62.776 10.5330 0.75 2.28 3.38 2.47 1.58579 6.10 6.74907 0.720656 4.91 233.660 31.14 31.20 1921.51 4.61966 44.320 209.017 28464.8 14.295 1515.79 692.94 512.427 2.65992 46.95612 55.463 4.21333 23.271 655.585 9.06392 39.654 1649.842 3207.145 7083.46 28085.8 128.612 110.195 627.893 4.90 6.66 6.30 13.42 10.45 4.64 6.33 0.73 2.18 2.43 8.07 4.50492 119.934 1.50450 8.848 76.270 3.66035 37.676 12.72 1365.694 5.50833 103.752 2.35 64.38 1.08503 63.82 2.94 126.157 2.36 3134.37 5.28 1634.65 3157.49 2.88 3155.67 2.56 9.90374 3581.76 15.54 1604.76 1.80107 3.74 9.32 2.52 5.80 1620.26 5.88 70.433 9.38883 0.84 2.54 3.76 2.74 1.75032 6.71 6.14016 0.788278 5.35 254.285 33.56 33.58 2043.14 4.90876 46.577 200.236 29628.0 14.865 1566.17 673.14 525.463 2.60027 47.99914 56.571 4.27091 22.993 662.907 9.00015 39.934 1642.144 3192.212 7052.86 28135.5 128.645 110.213 5.74 7.83 6.67 15.85 12.53 5.65 7.78 0.82 2.59 2.74 9.61 5.90961 OpenBenchmarking.org
Numenta Anomaly Benchmark Detector: Relative Entropy OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 30 60 90 120 150 SE +/- 0.090, N = 6 SE +/- 1.498, N = 4 9.716 119.934
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.3385 0.677 1.0155 1.354 1.6925 SE +/- 0.00135, N = 3 SE +/- 0.00207, N = 3 1.07871 1.50450 MIN: 0.96 MIN: 1.4 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Numenta Anomaly Benchmark Detector: Windowed Gaussian OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 2 4 6 8 10 SE +/- 0.012, N = 3 SE +/- 0.058, N = 3 6.466 8.848
Scikit-Learn Benchmark: Sparsify OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Sparsify m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.28, N = 3 104.15 76.27 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.8236 1.6472 2.4708 3.2944 4.118 SE +/- 0.00335, N = 3 SE +/- 0.01273, N = 3 2.75936 3.66035 MIN: 2.51 MIN: 3.45 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Numenta Anomaly Benchmark Detector: Contextual Anomaly Detector OSE OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Contextual Anomaly Detector OSE m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 9 18 27 36 45 SE +/- 0.17, N = 3 SE +/- 0.14, N = 3 30.66 37.68
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 10.37 12.72 MIN: 9.94 / MAX: 16.03 MIN: 12.47 / MAX: 17.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Scikit-Learn Benchmark: Isotonic / Logistic OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Isotonic / Logistic m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 300 600 900 1200 1500 SE +/- 4.00, N = 3 SE +/- 2.94, N = 3 1118.01 1365.69 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1.2394 2.4788 3.7182 4.9576 6.197 SE +/- 0.04068, N = 3 SE +/- 0.04121, N = 3 4.54620 5.50833 MIN: 3.79 MIN: 4.83 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Numenta Anomaly Benchmark Detector: Earthgecko Skyline OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 20 40 60 80 100 SE +/- 0.91, N = 15 SE +/- 0.60, N = 3 86.57 103.75
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.5288 1.0576 1.5864 2.1152 2.644 SE +/- 0.00, N = 3 SE +/- 0.03, N = 12 1.97 2.35 MIN: 1.85 / MAX: 6.58 MIN: 2.04 / MAX: 7.08 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 14 28 42 56 70 SE +/- 0.06, N = 3 SE +/- 0.24, N = 3 54.04 64.38 MIN: 52.55 / MAX: 64.52 MIN: 61.47 / MAX: 73.22 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.2441 0.4882 0.7323 0.9764 1.2205 SE +/- 0.003553, N = 3 SE +/- 0.006131, N = 3 0.912151 1.085030 MIN: 0.82 MIN: 1 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: CPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 14 28 42 56 70 SE +/- 0.05, N = 3 SE +/- 0.30, N = 12 53.79 63.82 MIN: 51.57 / MAX: 61.95 MIN: 60.84 / MAX: 93.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.6615 1.323 1.9845 2.646 3.3075 SE +/- 0.04, N = 3 SE +/- 0.05, N = 12 2.49 2.94 MIN: 2.33 / MAX: 5.65 MIN: 2.56 / MAX: 7.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Numenta Anomaly Benchmark Detector: KNN CAD OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: KNN CAD m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 30 60 90 120 150 SE +/- 0.38, N = 3 SE +/- 1.55, N = 4 107.12 126.16
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.531 1.062 1.593 2.124 2.655 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 2.01 2.36 MIN: 1.9 / MAX: 4.96 MIN: 2.24 / MAX: 5.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 700 1400 2100 2800 3500 SE +/- 22.64, N = 8 SE +/- 8.47, N = 3 2672.08 3134.37 MIN: 2490.39 MIN: 3100.85 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1.188 2.376 3.564 4.752 5.94 SE +/- 0.03, N = 3 SE +/- 0.03, N = 12 4.52 5.28 MIN: 4.35 / MAX: 8.37 MIN: 4.94 / MAX: 12.32 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 400 800 1200 1600 2000 SE +/- 2.23, N = 3 SE +/- 2.00, N = 3 1402.63 1634.65 MIN: 1343.03 MIN: 1607.74 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 700 1400 2100 2800 3500 SE +/- 5.55, N = 3 SE +/- 14.23, N = 3 2714.85 3157.49 MIN: 2634.21 MIN: 3102.28 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: FastestDet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.648 1.296 1.944 2.592 3.24 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 2.48 2.88 MIN: 2.34 / MAX: 6 MIN: 2.66 / MAX: 5.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 700 1400 2100 2800 3500 SE +/- 9.78, N = 3 SE +/- 8.76, N = 3 2718.50 3155.67 MIN: 2636.72 MIN: 3117.68 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.576 1.152 1.728 2.304 2.88 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 2.21 2.56 MIN: 2.08 / MAX: 5.13 MIN: 2.31 / MAX: 5.87 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 3 6 9 12 15 SE +/- 0.03672, N = 3 SE +/- 0.09024, N = 15 8.55150 9.90374 MIN: 7.52 MIN: 8.66 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Quant m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 800 1600 2400 3200 4000 SE +/- 3.46, N = 3 SE +/- 49.13, N = 3 3105.79 3581.76
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 13.60 15.54 MIN: 13.22 / MAX: 18.63 MIN: 13.95 / MAX: 19.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 300 600 900 1200 1500 SE +/- 17.30, N = 4 SE +/- 7.75, N = 3 1409.84 1604.76 MIN: 1312.69 MIN: 1553.39 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.4052 0.8104 1.2156 1.6208 2.026 SE +/- 0.02084, N = 3 SE +/- 0.01662, N = 6 1.58351 1.80107 MIN: 1.39 MIN: 1.54 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.8415 1.683 2.5245 3.366 4.2075 SE +/- 0.03, N = 3 SE +/- 0.06, N = 12 3.30 3.74 MIN: 3.09 / MAX: 6.22 MIN: 3.31 / MAX: 7.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 8.24 9.32 MIN: 7.85 / MAX: 12.18 MIN: 9.11 / MAX: 12.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.567 1.134 1.701 2.268 2.835 SE +/- 0.01, N = 3 SE +/- 0.04, N = 12 2.23 2.52 MIN: 2.13 / MAX: 5.1 MIN: 2.18 / MAX: 5.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1.305 2.61 3.915 5.22 6.525 SE +/- 0.01, N = 3 SE +/- 0.08, N = 12 5.14 5.80 MIN: 4.92 / MAX: 11.22 MIN: 5.11 / MAX: 9.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 300 600 900 1200 1500 SE +/- 4.68, N = 3 SE +/- 3.35, N = 3 1436.72 1620.26 MIN: 1361.41 MIN: 1590.57 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1.323 2.646 3.969 5.292 6.615 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 5.22 5.88 MIN: 4.91 / MAX: 8.27 MIN: 5.67 / MAX: 9.13 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Scikit-Learn Benchmark: Hist Gradient Boosting OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 16 32 48 64 80 SE +/- 0.08, N = 3 SE +/- 0.50, N = 15 62.78 70.43 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 3 6 9 12 15 SE +/- 0.10514, N = 3 SE +/- 0.00450, N = 3 10.53300 9.38883 MIN: 8.9 MIN: 9.03 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.189 0.378 0.567 0.756 0.945 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 0.75 0.84 MIN: 0.69 / MAX: 3.66 MIN: 0.77 / MAX: 3.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.5715 1.143 1.7145 2.286 2.8575 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 2.28 2.54 MIN: 2.14 / MAX: 5.25 MIN: 2.36 / MAX: 5.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.846 1.692 2.538 3.384 4.23 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 3.38 3.76 MIN: 3.17 / MAX: 6.42 MIN: 3.52 / MAX: 7.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.6165 1.233 1.8495 2.466 3.0825 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 2.47 2.74 MIN: 2.28 / MAX: 5.9 MIN: 2.54 / MAX: 6.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.3938 0.7876 1.1814 1.5752 1.969 SE +/- 0.00921, N = 3 SE +/- 0.00736, N = 3 1.58579 1.75032 MIN: 1.32 MIN: 1.61 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 6.10 6.71 MIN: 5.84 / MAX: 14.12 MIN: 6.47 / MAX: 10.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 2 4 6 8 10 SE +/- 0.11025, N = 12 SE +/- 0.02214, N = 3 6.74907 6.14016 MIN: 4.3 MIN: 5.37 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.1774 0.3548 0.5322 0.7096 0.887 SE +/- 0.006523, N = 15 SE +/- 0.009359, N = 3 0.720656 0.788278 MIN: 0.57 MIN: 0.7 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1.2038 2.4076 3.6114 4.8152 6.019 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 4.91 5.35 MIN: 4.69 / MAX: 11.39 MIN: 5.21 / MAX: 8.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Scikit-Learn Benchmark: TSNE MNIST Dataset OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: TSNE MNIST Dataset m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 60 120 180 240 300 SE +/- 0.28, N = 3 SE +/- 1.77, N = 3 233.66 254.29 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 8 16 24 32 40 SE +/- 0.46, N = 3 SE +/- 0.11, N = 12 31.14 33.56 MIN: 30.03 / MAX: 44.67 MIN: 30.78 / MAX: 59.11 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 8 16 24 32 40 SE +/- 0.02, N = 3 SE +/- 0.18, N = 3 31.20 33.58 MIN: 30.51 / MAX: 39.52 MIN: 30.97 / MAX: 56.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: SqueezeNet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 400 800 1200 1600 2000 SE +/- 5.32, N = 3 SE +/- 20.97, N = 3 1921.51 2043.14
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1.1045 2.209 3.3135 4.418 5.5225 SE +/- 0.04248, N = 6 SE +/- 0.01808, N = 3 4.61966 4.90876 MIN: 4.37 MIN: 4.75 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Scikit-Learn Benchmark: Tree OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Tree m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 11 22 33 44 55 SE +/- 0.36, N = 15 SE +/- 0.39, N = 15 44.32 46.58 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
Scikit-Learn Benchmark: SGDOneClassSVM OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: SGDOneClassSVM m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 50 100 150 200 250 SE +/- 2.78, N = 3 SE +/- 0.65, N = 3 209.02 200.24 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception V4 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 6K 12K 18K 24K 30K SE +/- 57.85, N = 3 SE +/- 104.54, N = 3 28464.8 29628.0
RNNoise OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 2020-06-28 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 14.30 14.87 1. (CC) gcc options: -O2 -pedantic -fvisibility=hidden -lm
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Mobilenet Float m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 300 600 900 1200 1500 SE +/- 9.91, N = 3 SE +/- 4.17, N = 3 1515.79 1566.17
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 150 300 450 600 750 SE +/- 5.43, N = 3 SE +/- 2.26, N = 3 692.94 673.14
Scikit-Learn Benchmark: Plot Fast KMeans OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Fast KMeans m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 110 220 330 440 550 SE +/- 2.66, N = 3 SE +/- 3.25, N = 3 512.43 525.46 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
oneDNN Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.5985 1.197 1.7955 2.394 2.9925 SE +/- 0.01990, N = 3 SE +/- 0.02758, N = 3 2.65992 2.60027 MIN: 2.43 MIN: 2.45 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
DeepSpeech Acceleration: CPU OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 11 22 33 44 55 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 46.96 48.00
Scikit-Learn Benchmark: MNIST Dataset OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: MNIST Dataset m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 13 26 39 52 65 SE +/- 0.50, N = 3 SE +/- 0.18, N = 3 55.46 56.57 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.961 1.922 2.883 3.844 4.805 SE +/- 0.06060, N = 3 SE +/- 0.02962, N = 3 4.21333 4.27091 MIN: 3.94 MIN: 4.05 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Numenta Anomaly Benchmark Detector: Bayesian Changepoint OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 6 12 18 24 30 SE +/- 0.20, N = 3 SE +/- 0.02, N = 3 23.27 22.99
Scikit-Learn Benchmark: SGD Regression OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: SGD Regression m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 140 280 420 560 700 SE +/- 2.72, N = 3 SE +/- 0.37, N = 3 655.59 662.91 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 3 6 9 12 15 SE +/- 0.04724, N = 3 SE +/- 0.00233, N = 3 9.06392 9.00015 MIN: 8.73 MIN: 8.75 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Scikit-Learn Benchmark: Plot Ward OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Ward m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 39.65 39.93 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
Scikit-Learn Benchmark: GLM OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: GLM m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 400 800 1200 1600 2000 SE +/- 2.64, N = 3 SE +/- 2.20, N = 3 1649.84 1642.14 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
Scikit-Learn Benchmark: Lasso OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Lasso m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 700 1400 2100 2800 3500 SE +/- 12.72, N = 3 SE +/- 9.69, N = 3 3207.15 3192.21 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: NASNet Mobile m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1500 3000 4500 6000 7500 SE +/- 47.37, N = 3 SE +/- 2.29, N = 3 7083.46 7052.86
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 6K 12K 18K 24K 30K SE +/- 247.53, N = 3 SE +/- 99.72, N = 3 28085.8 28135.5
Scikit-Learn Benchmark: Plot Hierarchical OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Hierarchical m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 30 60 90 120 150 SE +/- 1.33, N = 3 SE +/- 0.66, N = 3 128.61 128.65 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
Scikit-Learn Benchmark: Feature Expansions OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Feature Expansions m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.39, N = 3 110.20 110.21 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
Scikit-Learn Benchmark: Plot OMP vs. LARS OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot OMP vs. LARS m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 140 280 420 560 700 SE +/- 1.88, N = 3 627.89 1. (F9X) gfortran options: -O3 -fopenmp -fno-tree-vectorize -lm -lpthread -lgfortran -lc
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1.2915 2.583 3.8745 5.166 6.4575 SE +/- 0.03, N = 3 SE +/- 0.35, N = 3 4.90 5.74 MIN: 4.68 / MAX: 10.25 MIN: 5.13 / MAX: 11.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 2 4 6 8 10 SE +/- 0.07, N = 3 SE +/- 0.33, N = 3 6.66 7.83 MIN: 6.35 / MAX: 10.74 MIN: 7.27 / MAX: 11.84 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 2 4 6 8 10 SE +/- 0.27, N = 3 SE +/- 0.05, N = 11 6.30 6.67 MIN: 5.74 / MAX: 10.52 MIN: 6.28 / MAX: 10.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.58, N = 12 13.42 15.85 MIN: 12.96 / MAX: 17.77 MIN: 14.11 / MAX: 189.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 3 6 9 12 15 SE +/- 0.55, N = 3 SE +/- 0.05, N = 12 10.45 12.53 MIN: 9.44 / MAX: 15.88 MIN: 11.97 / MAX: 19.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1.2713 2.5426 3.8139 5.0852 6.3565 SE +/- 0.03, N = 3 SE +/- 0.13, N = 12 4.64 5.65 MIN: 4.44 / MAX: 7.49 MIN: 5.12 / MAX: 10.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.15, N = 12 6.33 7.78 MIN: 6.06 / MAX: 9.4 MIN: 6.82 / MAX: 11.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.1845 0.369 0.5535 0.738 0.9225 SE +/- 0.01, N = 3 SE +/- 0.01, N = 12 0.73 0.82 MIN: 0.69 / MAX: 3.56 MIN: 0.72 / MAX: 3.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.5828 1.1656 1.7484 2.3312 2.914 SE +/- 0.03, N = 3 SE +/- 0.05, N = 11 2.18 2.59 MIN: 2.01 / MAX: 5.91 MIN: 2.21 / MAX: 6.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 0.6165 1.233 1.8495 2.466 3.0825 SE +/- 0.01, N = 3 SE +/- 0.05, N = 12 2.43 2.74 MIN: 2.28 / MAX: 5.61 MIN: 2.42 / MAX: 6.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mobilenet m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.21, N = 12 8.07 9.61 MIN: 7.82 / MAX: 11.67 MIN: 8.79 / MAX: 298.81 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.1 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU m600_7940hs-96gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2023-09-01-2 m600_7940hs-guest-os-on-proxmox-host-60gb-5600mhz-16gb-igpu-performance-tpd-2tb-sn850x-2024-10-03 1.3297 2.6594 3.9891 5.3188 6.6485 SE +/- 0.13143, N = 15 SE +/- 0.03712, N = 3 4.50492 5.90961 MIN: 4.07 MIN: 5.63 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl
Phoronix Test Suite v10.8.5