pyt AMD Ryzen Threadripper PRO 7995WX 96-Cores testing with a HP 8B24 (U65 Ver. 01.01.04 BIOS) and NVIDIA RTX A4000 16GB on Ubuntu 23.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2401079-PTS-PYT7659364 .
pyt Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution a b c d AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads) HP 8B24 (U65 Ver. 01.01.04 BIOS) AMD Device 14a4 128GB 2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1 NVIDIA RTX A4000 16GB NVIDIA GA104 HD Audio ASUS VP28U Realtek RTL8111/8168/8411 Ubuntu 23.10 6.5.0-14-generic (x86_64) GNOME Shell 45.0 X Server 1.21.1.7 NVIDIA 535.129.03 4.6.0 OpenCL 3.0 CUDA 12.2.147 GCC 13.2.0 ext4 3840x2160 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Processor Details - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105 Python Details - Python 3.11.6 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
pyt pytorch: CPU - 1 - ResNet-50 pytorch: CPU - 1 - ResNet-152 pytorch: CPU - 16 - ResNet-50 pytorch: CPU - 32 - ResNet-50 pytorch: CPU - 64 - ResNet-50 pytorch: CPU - 16 - ResNet-152 pytorch: CPU - 256 - ResNet-50 pytorch: CPU - 32 - ResNet-152 pytorch: CPU - 512 - ResNet-50 pytorch: CPU - 64 - ResNet-152 pytorch: CPU - 256 - ResNet-152 pytorch: CPU - 512 - ResNet-152 pytorch: CPU - 1 - Efficientnet_v2_l pytorch: CPU - 16 - Efficientnet_v2_l pytorch: CPU - 32 - Efficientnet_v2_l pytorch: CPU - 64 - Efficientnet_v2_l pytorch: CPU - 256 - Efficientnet_v2_l pytorch: CPU - 512 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 1 - ResNet-50 pytorch: NVIDIA CUDA GPU - 1 - ResNet-152 pytorch: NVIDIA CUDA GPU - 16 - ResNet-50 pytorch: NVIDIA CUDA GPU - 32 - ResNet-50 pytorch: NVIDIA CUDA GPU - 64 - ResNet-50 pytorch: NVIDIA CUDA GPU - 16 - ResNet-152 pytorch: NVIDIA CUDA GPU - 256 - ResNet-50 pytorch: NVIDIA CUDA GPU - 32 - ResNet-152 pytorch: NVIDIA CUDA GPU - 512 - ResNet-50 pytorch: NVIDIA CUDA GPU - 64 - ResNet-152 pytorch: NVIDIA CUDA GPU - 256 - ResNet-152 pytorch: NVIDIA CUDA GPU - 512 - ResNet-152 pytorch: NVIDIA CUDA GPU - 1 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 16 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 32 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 64 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 256 - Efficientnet_v2_l pytorch: NVIDIA CUDA GPU - 512 - Efficientnet_v2_l a b c d 50.01 18.70 40.83 40.61 40.79 16.18 40.82 16.10 40.33 16.05 16.09 16.20 11.16 6.24 6.28 6.25 6.27 6.24 361.97 132.98 288.42 287.50 287.15 127.01 286.04 126.84 285.74 126.04 126.55 126.58 70.38 67.48 66.65 67.18 66.57 65.94 50.01 18.57 40.69 40.33 40.64 15.75 40.98 16.40 40.44 15.88 15.74 16.24 11.38 6.28 6.23 6.23 6.19 6.25 357.01 134.62 291.63 291.74 291.97 125.19 289.02 129.44 288.50 129.28 125.39 126.94 69.60 67.86 68.69 68.07 66.27 66.63 50.46 18.79 40.54 40.59 40.39 15.87 40.93 16.17 40.74 16.16 15.87 16.17 11.21 6.24 6.28 6.35 6.19 6.26 355.60 132.86 291.60 291.63 291.52 128.92 288.89 129.52 288.57 126.001462851 127.26 123.41 71.80 66.79 67.12 67.30 67.12 66.20 49.60 19.15 40.40 40.72 40.97 16.32 40.35 16.41 39.99 16.31 16.51 15.96 11.42 6.25 6.25 6.23 6.36 6.27 353.30 133.46 291.81 292.06 291.76 129.27 289.30 125.41 288.51 127.10 126.60 125.05 71.36 66.63 67.59 67.83 67.11 66.20 OpenBenchmarking.org
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 a b c d 11 22 33 44 55 SE +/- 0.35, N = 3 50.01 50.01 50.46 49.60 MIN: 41.31 / MAX: 52.57 MIN: 47.29 / MAX: 51.69 MIN: 42.91 / MAX: 52.85 MIN: 46.83 / MAX: 51.31
PyTorch Device: CPU - Batch Size: 1 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 a b c d 5 10 15 20 25 SE +/- 0.10, N = 3 18.70 18.57 18.79 19.15 MIN: 16.98 / MAX: 19.52 MIN: 18.2 / MAX: 19.14 MIN: 18.25 / MAX: 19.38 MIN: 18.8 / MAX: 19.48
PyTorch Device: CPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-50 a b c d 9 18 27 36 45 SE +/- 0.11, N = 3 40.83 40.69 40.54 40.40 MIN: 37.32 / MAX: 42.16 MIN: 37.2 / MAX: 41.69 MIN: 37.73 / MAX: 41.72 MIN: 37.83 / MAX: 41.64
PyTorch Device: CPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: ResNet-50 a b c d 9 18 27 36 45 SE +/- 0.11, N = 3 40.61 40.33 40.59 40.72 MIN: 36.37 / MAX: 42.03 MIN: 37.66 / MAX: 41.57 MIN: 37.53 / MAX: 41.98 MIN: 38.11 / MAX: 41.8
PyTorch Device: CPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 a b c d 9 18 27 36 45 SE +/- 0.09, N = 3 40.79 40.64 40.39 40.97 MIN: 38.02 / MAX: 42.17 MIN: 38.74 / MAX: 42.14 MIN: 37.31 / MAX: 41.6 MIN: 38.49 / MAX: 42.31
PyTorch Device: CPU - Batch Size: 16 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-152 a b c d 4 8 12 16 20 SE +/- 0.12, N = 3 16.18 15.75 15.87 16.32 MIN: 15.51 / MAX: 16.68 MIN: 15.47 / MAX: 15.96 MIN: 15.29 / MAX: 16.21 MIN: 16.02 / MAX: 16.63
PyTorch Device: CPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 a b c d 9 18 27 36 45 SE +/- 0.04, N = 3 40.82 40.98 40.93 40.35 MIN: 37.5 / MAX: 42.24 MIN: 37.68 / MAX: 42.28 MIN: 37.58 / MAX: 42.04 MIN: 38.37 / MAX: 41.61
PyTorch Device: CPU - Batch Size: 32 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: ResNet-152 a b c d 4 8 12 16 20 SE +/- 0.12, N = 3 16.10 16.40 16.17 16.41 MIN: 15.51 / MAX: 16.66 MIN: 16.04 / MAX: 16.64 MIN: 15.85 / MAX: 16.44 MIN: 16 / MAX: 16.65
PyTorch Device: CPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 a b c d 9 18 27 36 45 SE +/- 0.03, N = 3 40.33 40.44 40.74 39.99 MIN: 36.91 / MAX: 41.68 MIN: 38.09 / MAX: 41.52 MIN: 38.28 / MAX: 41.79 MIN: 37.13 / MAX: 41.16
PyTorch Device: CPU - Batch Size: 64 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 64 - Model: ResNet-152 a b c d 4 8 12 16 20 SE +/- 0.14, N = 3 16.05 15.88 16.16 16.31 MIN: 15.53 / MAX: 16.58 MIN: 15.64 / MAX: 16.11 MIN: 15.77 / MAX: 16.39 MIN: 15.81 / MAX: 16.6
PyTorch Device: CPU - Batch Size: 256 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 a b c d 4 8 12 16 20 SE +/- 0.21, N = 3 16.09 15.74 15.87 16.51 MIN: 15.51 / MAX: 16.77 MIN: 15.42 / MAX: 16 MIN: 15.48 / MAX: 16.09 MIN: 16.1 / MAX: 16.76
PyTorch Device: CPU - Batch Size: 512 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: ResNet-152 a b c d 4 8 12 16 20 SE +/- 0.13, N = 3 16.20 16.24 16.17 15.96 MIN: 15.68 / MAX: 16.65 MIN: 16 / MAX: 16.49 MIN: 15.8 / MAX: 16.39 MIN: 15.52 / MAX: 16.2
PyTorch Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l a b c d 3 6 9 12 15 SE +/- 0.13, N = 3 11.16 11.38 11.21 11.42 MIN: 10.76 / MAX: 11.57 MIN: 11.17 / MAX: 11.58 MIN: 11.06 / MAX: 11.41 MIN: 11.27 / MAX: 11.64
PyTorch Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l a b c d 2 4 6 8 10 SE +/- 0.00, N = 3 6.24 6.28 6.24 6.25 MIN: 5.66 / MAX: 6.57 MIN: 5.73 / MAX: 6.59 MIN: 5.68 / MAX: 6.54 MIN: 5.76 / MAX: 6.54
PyTorch Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l a b c d 2 4 6 8 10 SE +/- 0.03, N = 3 6.28 6.23 6.28 6.25 MIN: 5.73 / MAX: 6.61 MIN: 5.64 / MAX: 6.54 MIN: 5.72 / MAX: 6.6 MIN: 5.72 / MAX: 6.55
PyTorch Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l a b c d 2 4 6 8 10 SE +/- 0.01, N = 3 6.25 6.23 6.35 6.23 MIN: 5.63 / MAX: 6.58 MIN: 5.76 / MAX: 6.58 MIN: 5.68 / MAX: 6.64 MIN: 5.65 / MAX: 6.55
PyTorch Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l a b c d 2 4 6 8 10 SE +/- 0.01, N = 3 6.27 6.19 6.19 6.36 MIN: 5.64 / MAX: 6.59 MIN: 5.65 / MAX: 6.52 MIN: 5.79 / MAX: 6.52 MIN: 5.83 / MAX: 6.65
PyTorch Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l a b c d 2 4 6 8 10 SE +/- 0.01, N = 3 6.24 6.25 6.26 6.27 MIN: 5.55 / MAX: 6.61 MIN: 5.71 / MAX: 6.55 MIN: 5.73 / MAX: 6.65 MIN: 5.68 / MAX: 6.58
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50 a b c d 80 160 240 320 400 SE +/- 0.86, N = 3 361.97 357.01 355.60 353.30 MIN: 275.89 / MAX: 372.99 MIN: 279.97 / MAX: 368.92 MIN: 253.71 / MAX: 368.08 MIN: 256.99 / MAX: 364.75
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152 a b c d 30 60 90 120 150 SE +/- 1.79, N = 3 132.98 134.62 132.86 133.46 MIN: 109 / MAX: 139.03 MIN: 120.29 / MAX: 137.09 MIN: 118.76 / MAX: 135.2 MIN: 120.4 / MAX: 136
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50 a b c d 60 120 180 240 300 SE +/- 0.75, N = 3 288.42 291.63 291.60 291.81 MIN: 161 / MAX: 307.66 MIN: 177.88 / MAX: 309.38 MIN: 170.99 / MAX: 308.54 MIN: 173.47 / MAX: 308.79
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50 a b c d 60 120 180 240 300 SE +/- 0.61, N = 3 287.50 291.74 291.63 292.06 MIN: 162.04 / MAX: 306.4 MIN: 166.05 / MAX: 307.97 MIN: 172.75 / MAX: 308.18 MIN: 174.72 / MAX: 308
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50 a b c d 60 120 180 240 300 SE +/- 0.63, N = 3 287.15 291.97 291.52 291.76 MIN: 158.4 / MAX: 306.18 MIN: 165.71 / MAX: 307.55 MIN: 165.73 / MAX: 307.7 MIN: 164.85 / MAX: 307.84
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152 a b c d 30 60 90 120 150 SE +/- 0.37, N = 3 127.01 125.19 128.92 129.27 MIN: 84.3 / MAX: 133.47 MIN: 85.51 / MAX: 130.24 MIN: 85.34 / MAX: 134.89 MIN: 85.34 / MAX: 134.51
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50 a b c d 60 120 180 240 300 SE +/- 0.24, N = 3 286.04 289.02 288.89 289.30 MIN: 159.06 / MAX: 306.89 MIN: 162.8 / MAX: 306.2 MIN: 163.12 / MAX: 306.42 MIN: 163.39 / MAX: 309.15
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152 a b c d 30 60 90 120 150 SE +/- 0.95, N = 3 126.84 129.44 129.52 125.41 MIN: 84.12 / MAX: 134.23 MIN: 82.93 / MAX: 135.75 MIN: 83.58 / MAX: 135.06 MIN: 86.22 / MAX: 129.99
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50 a b c d 60 120 180 240 300 SE +/- 0.18, N = 3 285.74 288.50 288.57 288.51 MIN: 155.06 / MAX: 305.6 MIN: 158.95 / MAX: 305.84 MIN: 160.08 / MAX: 306.4 MIN: 160.15 / MAX: 306.96
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152 a b c d 30 60 90 120 150 SE +/- 0.61, N = 3 126.04 129.28 126.00 127.10 MIN: 82.85 / MAX: 132.47 MIN: 87.37 / MAX: 135.32 MIN: 84.46 / MAX: 131.5 MIN: 86.66 / MAX: 132.45
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152 a b c d 30 60 90 120 150 SE +/- 0.24, N = 3 126.55 125.39 127.26 126.60 MIN: 83.28 / MAX: 132.07 MIN: 86.14 / MAX: 129.58 MIN: 83.4 / MAX: 132.61 MIN: 85.8 / MAX: 131.88
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152 OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152 a b c d 30 60 90 120 150 SE +/- 0.41, N = 3 126.58 126.94 123.41 125.05 MIN: 84.07 / MAX: 132.98 MIN: 84.98 / MAX: 132.33 MIN: 83.78 / MAX: 128.02 MIN: 85.26 / MAX: 130.68
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_l a b c d 16 32 48 64 80 SE +/- 0.68, N = 3 70.38 69.60 71.80 71.36 MIN: 61.79 / MAX: 72.15 MIN: 61.72 / MAX: 70.71 MIN: 63.35 / MAX: 73.09 MIN: 63.42 / MAX: 72.31
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_l a b c d 15 30 45 60 75 SE +/- 0.16, N = 3 67.48 67.86 66.79 66.63 MIN: 56.83 / MAX: 69.22 MIN: 57.92 / MAX: 69.28 MIN: 57.46 / MAX: 68.25 MIN: 56.78 / MAX: 68.44
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_l a b c d 15 30 45 60 75 SE +/- 0.50, N = 3 66.65 68.69 67.12 67.59 MIN: 55.99 / MAX: 68.52 MIN: 58.81 / MAX: 70.38 MIN: 55.88 / MAX: 68.73 MIN: 58.11 / MAX: 68.86
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_l a b c d 15 30 45 60 75 SE +/- 0.29, N = 3 67.18 68.07 67.30 67.83 MIN: 56.83 / MAX: 69.18 MIN: 56.37 / MAX: 69.63 MIN: 57.99 / MAX: 68.74 MIN: 57.39 / MAX: 69.34
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_l a b c d 15 30 45 60 75 SE +/- 0.23, N = 3 66.57 66.27 67.12 67.11 MIN: 55.8 / MAX: 68.27 MIN: 57.1 / MAX: 67.74 MIN: 56.29 / MAX: 68.56 MIN: 56.28 / MAX: 68.34
PyTorch Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_l a b c d 15 30 45 60 75 SE +/- 0.87, N = 3 65.94 66.63 66.20 66.20 MIN: 55.7 / MAX: 68.83 MIN: 57.06 / MAX: 67.92 MIN: 55.97 / MAX: 67.74 MIN: 55.93 / MAX: 67.54
Phoronix Test Suite v10.8.4