somervillePyTorchFULL AMD Ryzen 9 9950X 16-Core testing with a ASUS PRIME B650M-A II (3201 BIOS) and Gigabyte NVIDIA GeForce RTX 2070 SUPER 8GB on Ubuntu 24.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2501271-NE-SOMERVILL26&grs .
somervillePyTorchFULL Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Display Server Display Driver OpenCL Compiler File-System Screen Resolution run1 AMD Ryzen 9 9950X 16-Core @ 5.75GHz (16 Cores / 32 Threads) ASUS PRIME B650M-A II (3201 BIOS) AMD Device 14d8 4 x 48GB DDR5-3600MT/s G Skill F5-6800J3446F48G 2000GB Samsung SSD 980 PRO 2TB Gigabyte NVIDIA GeForce RTX 2070 SUPER 8GB NVIDIA TU104 HD Audio VS2447 100Hz 2 x Intel 10-Gigabit X540-AT2 + Realtek RTL8125 2.5GbE Ubuntu 24.04 6.8.0-51-generic (x86_64) X Server 1.21.1.11 NVIDIA OpenCL 3.0 CUDA 12.4.131 GCC 13.3.0 + CUDA 12.4 ext4 1920x1080 OpenBenchmarking.org - Transparent Huge Pages: madvise - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xb404023 - Python 3.12.3 - 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: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
somervillePyTorchFULL pytorch: NVIDIA CUDA GPU - 512 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 256 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 64 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 32 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 16 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 1 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 512 - ResNet-152 pytorch: NVIDIA CUDA GPU - 256 - ResNet-152 pytorch: NVIDIA CUDA GPU - 64 - ResNet-152 pytorch: NVIDIA CUDA GPU - 512 - ResNet-50 pytorch: NVIDIA CUDA GPU - 32 - ResNet-152 pytorch: NVIDIA CUDA GPU - 256 - ResNet-50 pytorch: NVIDIA CUDA GPU - 16 - ResNet-152 pytorch: NVIDIA CUDA GPU - 64 - ResNet-50 pytorch: NVIDIA CUDA GPU - 32 - ResNet-50 pytorch: NVIDIA CUDA GPU - 16 - ResNet-50 pytorch: NVIDIA CUDA GPU - 1 - ResNet-152 pytorch: NVIDIA CUDA GPU - 1 - ResNet-50 pytorch: CPU - 512 - Efficientnet_v2_l pytorch: CPU - 256 - Efficientnet_v2_l pytorch: CPU - 64 - Efficientnet_v2_l pytorch: CPU - 32 - Efficientnet_v2_l pytorch: CPU - 16 - Efficientnet_v2_l pytorch: CPU - 1 - Efficientnet_v2_l pytorch: CPU - 512 - ResNet-152 pytorch: CPU - 256 - ResNet-152 pytorch: CPU - 64 - ResNet-152 pytorch: CPU - 512 - ResNet-50 pytorch: CPU - 32 - ResNet-152 pytorch: CPU - 256 - ResNet-50 pytorch: CPU - 16 - ResNet-152 pytorch: CPU - 64 - ResNet-50 pytorch: CPU - 32 - ResNet-50 pytorch: CPU - 16 - ResNet-50 pytorch: CPU - 1 - ResNet-152 pytorch: CPU - 1 - ResNet-50 run1 58.24 58.27 58.26 58.30 58.38 104.20 85.67 85.68 85.85 207.79 85.82 207.52 85.97 208.44 208.57 208.83 131.72 325.51 12.66 12.65 12.42 12.69 12.64 16.23 21.21 21.28 21.20 50.91 21.26 52.01 21.07 52.46 52.01 53.13 29.44 73.77 OpenBenchmarking.org
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l run1 13 26 39 52 65 SE +/- 0.04, N = 3 58.24 MIN: 51.17 / MAX: 59.03
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l run1 13 26 39 52 65 SE +/- 0.05, N = 3 58.27 MIN: 54.21 / MAX: 59.2
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l run1 13 26 39 52 65 SE +/- 0.07, N = 3 58.26 MIN: 51.34 / MAX: 59.25
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l run1 13 26 39 52 65 SE +/- 0.06, N = 3 58.30 MIN: 52.73 / MAX: 59.25
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l run1 13 26 39 52 65 SE +/- 0.05, N = 3 58.38 MIN: 50.27 / MAX: 59.3
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l run1 20 40 60 80 100 SE +/- 0.04, N = 3 104.20 MIN: 89.05 / MAX: 105.94
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152 run1 20 40 60 80 100 SE +/- 0.08, N = 3 85.67 MIN: 82.97 / MAX: 87.07
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152 run1 20 40 60 80 100 SE +/- 0.07, N = 3 85.68 MIN: 83.44 / MAX: 87.17
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152 run1 20 40 60 80 100 SE +/- 0.07, N = 3 85.85 MIN: 83.46 / MAX: 87.19
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50 run1 50 100 150 200 250 SE +/- 0.17, N = 3 207.79 MIN: 192.71 / MAX: 209.46
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152 run1 20 40 60 80 100 SE +/- 0.06, N = 3 85.82 MIN: 83.62 / MAX: 87.16
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50 run1 50 100 150 200 250 SE +/- 0.19, N = 3 207.52 MIN: 192.76 / MAX: 209.28
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152 run1 20 40 60 80 100 SE +/- 0.14, N = 3 85.97 MIN: 83.42 / MAX: 87.55
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50 run1 50 100 150 200 250 SE +/- 0.22, N = 3 208.44 MIN: 151.51 / MAX: 210.37
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50 run1 50 100 150 200 250 SE +/- 0.18, N = 3 208.57 MIN: 193.37 / MAX: 210.52
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50 run1 50 100 150 200 250 SE +/- 0.19, N = 3 208.83 MIN: 193.54 / MAX: 210.94
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152 run1 30 60 90 120 150 SE +/- 0.25, N = 3 131.72 MIN: 100.93 / MAX: 132.78
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50 run1 70 140 210 280 350 SE +/- 0.37, N = 3 325.51 MIN: 314.65 / MAX: 329.04
PyTorch Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l run1 3 6 9 12 15 SE +/- 0.08, N = 3 12.66 MIN: 11.08 / MAX: 13.25
PyTorch Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l run1 3 6 9 12 15 SE +/- 0.05, N = 3 12.65 MIN: 11.39 / MAX: 13.17
PyTorch Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l run1 3 6 9 12 15 SE +/- 0.08, N = 3 12.42 MIN: 10.74 / MAX: 13.24
PyTorch Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l run1 3 6 9 12 15 SE +/- 0.02, N = 3 12.69 MIN: 11.27 / MAX: 13.14
PyTorch Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l run1 3 6 9 12 15 SE +/- 0.06, N = 3 12.64 MIN: 11.04 / MAX: 13.16
PyTorch Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l run1 4 8 12 16 20 SE +/- 0.06, N = 3 16.23 MIN: 15.83 / MAX: 16.5
PyTorch Device: CPU - Batch Size: 512 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-152 run1 5 10 15 20 25 SE +/- 0.23, N = 3 21.21 MIN: 19.83 / MAX: 21.7
PyTorch Device: CPU - Batch Size: 256 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 run1 5 10 15 20 25 SE +/- 0.13, N = 3 21.28 MIN: 18.47 / MAX: 21.73
PyTorch Device: CPU - Batch Size: 64 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-152 run1 5 10 15 20 25 SE +/- 0.23, N = 4 21.20 MIN: 18.7 / MAX: 21.86
PyTorch Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 run1 11 22 33 44 55 SE +/- 0.39, N = 3 50.91 MIN: 48.68 / MAX: 51.95
PyTorch Device: CPU - Batch Size: 32 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 32 - Model: ResNet-152 run1 5 10 15 20 25 SE +/- 0.24, N = 3 21.26 MIN: 18.19 / MAX: 22
PyTorch Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 run1 12 24 36 48 60 SE +/- 0.62, N = 4 52.01 MIN: 47.86 / MAX: 53.15
PyTorch Device: CPU - Batch Size: 16 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 16 - Model: ResNet-152 run1 5 10 15 20 25 SE +/- 0.11, N = 3 21.07 MIN: 19.52 / MAX: 21.47
PyTorch Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 run1 12 24 36 48 60 SE +/- 0.19, N = 3 52.46 MIN: 45.47 / MAX: 53.68
PyTorch Device: CPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 32 - Model: ResNet-50 run1 12 24 36 48 60 SE +/- 0.27, N = 3 52.01 MIN: 48.14 / MAX: 53.17
PyTorch Device: CPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 16 - Model: ResNet-50 run1 12 24 36 48 60 SE +/- 0.17, N = 3 53.13 MIN: 46.44 / MAX: 53.96
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 run1 7 14 21 28 35 SE +/- 0.20, N = 3 29.44 MIN: 27.2 / MAX: 30.14
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 run1 16 32 48 64 80 SE +/- 0.24, N = 3 73.77 MIN: 67.93 / MAX: 74.81
Phoronix Test Suite v10.8.5