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.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2401079-PTS-PYT7659364
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

Statistics

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

Graph Settings

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

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
a
January 07
  2 Hours, 24 Minutes
b
January 07
  48 Minutes
c
January 07
  48 Minutes
d
January 07
  48 Minutes
Invert Hiding All Results Option
  1 Hour, 12 Minutes

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


pytOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads)HP 8B24 (U65 Ver. 01.01.04 BIOS)AMD Device 14a4128GB2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1NVIDIA RTX A4000 16GBNVIDIA GA104 HD AudioASUS VP28URealtek RTL8111/8168/8411Ubuntu 23.106.5.0-14-generic (x86_64)GNOME Shell 45.0X Server 1.21.1.7NVIDIA 535.129.034.6.0OpenCL 3.0 CUDA 12.2.147GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionPyt BenchmarksSystem Logs- Transparent Huge Pages: madvise- Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105- Python 3.11.6- 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

abcdResult OverviewPhoronix Test Suite100%101%102%104%105%PyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchPyTorchCPU - 256 - ResNet-152CPU - 16 - ResNet-152NVIDIA CUDA GPU - 32 - ResNet-152NVIDIA CUDA GPU - 16 - ResNet-152NVIDIA CUDA GPU - 1 - Efficientnet_v2_lCPU - 1 - ResNet-152NVIDIA CUDA GPU - 32 - Efficientnet_v2_lNVIDIA CUDA GPU - 512 - ResNet-152CPU - 256 - Efficientnet_v2_lCPU - 64 - ResNet-152NVIDIA CUDA GPU - 64 - ResNet-152NVIDIA CUDA GPU - 1 - ResNet-50CPU - 1 - Efficientnet_v2_lCPU - 64 - Efficientnet_v2_lCPU - 32 - ResNet-152CPU - 512 - ResNet-50NVIDIA CUDA GPU - 16 - Efficientnet_v2_lCPU - 512 - ResNet-152CPU - 1 - ResNet-50NVIDIA CUDA GPU - 64 - ResNet-50NVIDIA CUDA GPU - 32 - ResNet-50CPU - 256 - ResNet-50NVIDIA CUDA GPU - 256 - ResNet-152CPU - 64 - ResNet-50NVIDIA CUDA GPU - 64 - Efficientnet_v2_lNVIDIA CUDA GPU - 1 - ResNet-152NVIDIA CUDA GPU - 256 - Efficientnet_v2_lNVIDIA CUDA GPU - 16 - ResNet-50NVIDIA CUDA GPU - 256 - ResNet-50CPU - 16 - ResNet-50NVIDIA CUDA GPU - 512 - Efficientnet_v2_lNVIDIA CUDA GPU - 512 - ResNet-50CPU - 32 - ResNet-50CPU - 32 - Efficientnet_v2_lCPU - 16 - Efficientnet_v2_lCPU - 512 - Efficientnet_v2_l

pytpytorch: CPU - 1 - ResNet-50pytorch: CPU - 1 - ResNet-152pytorch: CPU - 16 - ResNet-50pytorch: CPU - 32 - ResNet-50pytorch: CPU - 64 - ResNet-50pytorch: CPU - 16 - ResNet-152pytorch: CPU - 256 - ResNet-50pytorch: CPU - 32 - ResNet-152pytorch: CPU - 512 - ResNet-50pytorch: CPU - 64 - ResNet-152pytorch: CPU - 256 - ResNet-152pytorch: CPU - 512 - ResNet-152pytorch: CPU - 1 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 64 - Efficientnet_v2_lpytorch: CPU - 256 - Efficientnet_v2_lpytorch: CPU - 512 - Efficientnet_v2_lpytorch: NVIDIA CUDA GPU - 1 - ResNet-50pytorch: NVIDIA CUDA GPU - 1 - ResNet-152pytorch: NVIDIA CUDA GPU - 16 - ResNet-50pytorch: NVIDIA CUDA GPU - 32 - ResNet-50pytorch: NVIDIA CUDA GPU - 64 - ResNet-50pytorch: NVIDIA CUDA GPU - 16 - ResNet-152pytorch: NVIDIA CUDA GPU - 256 - ResNet-50pytorch: NVIDIA CUDA GPU - 32 - ResNet-152pytorch: NVIDIA CUDA GPU - 512 - ResNet-50pytorch: NVIDIA CUDA GPU - 64 - ResNet-152pytorch: NVIDIA CUDA GPU - 256 - ResNet-152pytorch: NVIDIA CUDA GPU - 512 - ResNet-152pytorch: NVIDIA CUDA GPU - 1 - Efficientnet_v2_lpytorch: NVIDIA CUDA GPU - 16 - Efficientnet_v2_lpytorch: NVIDIA CUDA GPU - 32 - Efficientnet_v2_lpytorch: NVIDIA CUDA GPU - 64 - Efficientnet_v2_lpytorch: NVIDIA CUDA GPU - 256 - Efficientnet_v2_lpytorch: NVIDIA CUDA GPU - 512 - Efficientnet_v2_labcd50.0118.7040.8340.6140.7916.1840.8216.1040.3316.0516.0916.2011.166.246.286.256.276.24361.97132.98288.42287.50287.15127.01286.04126.84285.74126.04126.55126.5870.3867.4866.6567.1866.5765.9450.0118.5740.6940.3340.6415.7540.9816.4040.4415.8815.7416.2411.386.286.236.236.196.25357.01134.62291.63291.74291.97125.19289.02129.44288.50129.28125.39126.9469.6067.8668.6968.0766.2766.6350.4618.7940.5440.5940.3915.8740.9316.1740.7416.1615.8716.1711.216.246.286.356.196.26355.60132.86291.60291.63291.52128.92288.89129.52288.57126.001462851127.26123.4171.8066.7967.1267.3067.1266.2049.6019.1540.4040.7240.9716.3240.3516.4139.9916.3116.5115.9611.426.256.256.236.366.27353.30133.46291.81292.06291.76129.27289.30125.41288.51127.10126.60125.0571.3666.6367.5967.8367.1166.20OpenBenchmarking.org

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Currently this test profile is catered to CPU-based testing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50abcd1122334455SE +/- 0.35, N = 350.0150.0150.4649.60MIN: 41.31 / MAX: 52.57MIN: 47.29 / MAX: 51.69MIN: 42.91 / MAX: 52.85MIN: 46.83 / MAX: 51.31
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50abcd1020304050Min: 49.32 / Avg: 50.01 / Max: 50.42

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152abcd510152025SE +/- 0.10, N = 318.7018.5718.7919.15MIN: 16.98 / MAX: 19.52MIN: 18.2 / MAX: 19.14MIN: 18.25 / MAX: 19.38MIN: 18.8 / MAX: 19.48
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152abcd510152025Min: 18.51 / Avg: 18.7 / Max: 18.87

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50abcd918273645SE +/- 0.11, N = 340.8340.6940.5440.40MIN: 37.32 / MAX: 42.16MIN: 37.2 / MAX: 41.69MIN: 37.73 / MAX: 41.72MIN: 37.83 / MAX: 41.64
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50abcd816243240Min: 40.69 / Avg: 40.83 / Max: 41.04

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50abcd918273645SE +/- 0.11, N = 340.6140.3340.5940.72MIN: 36.37 / MAX: 42.03MIN: 37.66 / MAX: 41.57MIN: 37.53 / MAX: 41.98MIN: 38.11 / MAX: 41.8
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50abcd816243240Min: 40.46 / Avg: 40.61 / Max: 40.83

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50abcd918273645SE +/- 0.09, N = 340.7940.6440.3940.97MIN: 38.02 / MAX: 42.17MIN: 38.74 / MAX: 42.14MIN: 37.31 / MAX: 41.6MIN: 38.49 / MAX: 42.31
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50abcd918273645Min: 40.62 / Avg: 40.79 / Max: 40.94

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152abcd48121620SE +/- 0.12, N = 316.1815.7515.8716.32MIN: 15.51 / MAX: 16.68MIN: 15.47 / MAX: 15.96MIN: 15.29 / MAX: 16.21MIN: 16.02 / MAX: 16.63
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152abcd48121620Min: 15.97 / Avg: 16.18 / Max: 16.38

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50abcd918273645SE +/- 0.04, N = 340.8240.9840.9340.35MIN: 37.5 / MAX: 42.24MIN: 37.68 / MAX: 42.28MIN: 37.58 / MAX: 42.04MIN: 38.37 / MAX: 41.61
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50abcd918273645Min: 40.73 / Avg: 40.82 / Max: 40.86

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152abcd48121620SE +/- 0.12, N = 316.1016.4016.1716.41MIN: 15.51 / MAX: 16.66MIN: 16.04 / MAX: 16.64MIN: 15.85 / MAX: 16.44MIN: 16 / MAX: 16.65
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152abcd48121620Min: 15.97 / Avg: 16.1 / Max: 16.35

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-50abcd918273645SE +/- 0.03, N = 340.3340.4440.7439.99MIN: 36.91 / MAX: 41.68MIN: 38.09 / MAX: 41.52MIN: 38.28 / MAX: 41.79MIN: 37.13 / MAX: 41.16
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-50abcd816243240Min: 40.3 / Avg: 40.33 / Max: 40.4

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152abcd48121620SE +/- 0.14, N = 316.0515.8816.1616.31MIN: 15.53 / MAX: 16.58MIN: 15.64 / MAX: 16.11MIN: 15.77 / MAX: 16.39MIN: 15.81 / MAX: 16.6
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152abcd48121620Min: 15.83 / Avg: 16.05 / Max: 16.31

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-152abcd48121620SE +/- 0.21, N = 316.0915.7415.8716.51MIN: 15.51 / MAX: 16.77MIN: 15.42 / MAX: 16MIN: 15.48 / MAX: 16.09MIN: 16.1 / MAX: 16.76
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-152abcd48121620Min: 15.78 / Avg: 16.09 / Max: 16.49

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-152abcd48121620SE +/- 0.13, N = 316.2016.2416.1715.96MIN: 15.68 / MAX: 16.65MIN: 16 / MAX: 16.49MIN: 15.8 / MAX: 16.39MIN: 15.52 / MAX: 16.2
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-152abcd48121620Min: 16.03 / Avg: 16.2 / Max: 16.45

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_labcd3691215SE +/- 0.13, N = 311.1611.3811.2111.42MIN: 10.76 / MAX: 11.57MIN: 11.17 / MAX: 11.58MIN: 11.06 / MAX: 11.41MIN: 11.27 / MAX: 11.64
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_labcd3691215Min: 10.92 / Avg: 11.16 / Max: 11.38

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_labcd246810SE +/- 0.00, N = 36.246.286.246.25MIN: 5.66 / MAX: 6.57MIN: 5.73 / MAX: 6.59MIN: 5.68 / MAX: 6.54MIN: 5.76 / MAX: 6.54
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_labcd3691215Min: 6.24 / Avg: 6.24 / Max: 6.25

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_labcd246810SE +/- 0.03, N = 36.286.236.286.25MIN: 5.73 / MAX: 6.61MIN: 5.64 / MAX: 6.54MIN: 5.72 / MAX: 6.6MIN: 5.72 / MAX: 6.55
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_labcd3691215Min: 6.25 / Avg: 6.28 / Max: 6.33

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_labcd246810SE +/- 0.01, N = 36.256.236.356.23MIN: 5.63 / MAX: 6.58MIN: 5.76 / MAX: 6.58MIN: 5.68 / MAX: 6.64MIN: 5.65 / MAX: 6.55
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_labcd3691215Min: 6.23 / Avg: 6.25 / Max: 6.27

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_labcd246810SE +/- 0.01, N = 36.276.196.196.36MIN: 5.64 / MAX: 6.59MIN: 5.65 / MAX: 6.52MIN: 5.79 / MAX: 6.52MIN: 5.83 / MAX: 6.65
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_labcd3691215Min: 6.25 / Avg: 6.27 / Max: 6.28

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_labcd246810SE +/- 0.01, N = 36.246.256.266.27MIN: 5.55 / MAX: 6.61MIN: 5.71 / MAX: 6.55MIN: 5.73 / MAX: 6.65MIN: 5.68 / MAX: 6.58
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_labcd3691215Min: 6.22 / Avg: 6.24 / Max: 6.26

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50abcd80160240320400SE +/- 0.86, N = 3361.97357.01355.60353.30MIN: 275.89 / MAX: 372.99MIN: 279.97 / MAX: 368.92MIN: 253.71 / MAX: 368.08MIN: 256.99 / MAX: 364.75
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-50abcd60120180240300Min: 360.74 / Avg: 361.97 / Max: 363.63

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152abcd306090120150SE +/- 1.79, N = 3132.98134.62132.86133.46MIN: 109 / MAX: 139.03MIN: 120.29 / MAX: 137.09MIN: 118.76 / MAX: 135.2MIN: 120.4 / MAX: 136
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: ResNet-152abcd306090120150Min: 130.59 / Avg: 132.98 / Max: 136.49

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50abcd60120180240300SE +/- 0.75, N = 3288.42291.63291.60291.81MIN: 161 / MAX: 307.66MIN: 177.88 / MAX: 309.38MIN: 170.99 / MAX: 308.54MIN: 173.47 / MAX: 308.79
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-50abcd50100150200250Min: 287.34 / Avg: 288.42 / Max: 289.85

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50abcd60120180240300SE +/- 0.61, N = 3287.50291.74291.63292.06MIN: 162.04 / MAX: 306.4MIN: 166.05 / MAX: 307.97MIN: 172.75 / MAX: 308.18MIN: 174.72 / MAX: 308
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-50abcd50100150200250Min: 286.61 / Avg: 287.5 / Max: 288.67

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50abcd60120180240300SE +/- 0.63, N = 3287.15291.97291.52291.76MIN: 158.4 / MAX: 306.18MIN: 165.71 / MAX: 307.55MIN: 165.73 / MAX: 307.7MIN: 164.85 / MAX: 307.84
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-50abcd50100150200250Min: 286.13 / Avg: 287.15 / Max: 288.29

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152abcd306090120150SE +/- 0.37, N = 3127.01125.19128.92129.27MIN: 84.3 / MAX: 133.47MIN: 85.51 / MAX: 130.24MIN: 85.34 / MAX: 134.89MIN: 85.34 / MAX: 134.51
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: ResNet-152abcd20406080100Min: 126.43 / Avg: 127.01 / Max: 127.69

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50abcd60120180240300SE +/- 0.24, N = 3286.04289.02288.89289.30MIN: 159.06 / MAX: 306.89MIN: 162.8 / MAX: 306.2MIN: 163.12 / MAX: 306.42MIN: 163.39 / MAX: 309.15
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-50abcd50100150200250Min: 285.7 / Avg: 286.04 / Max: 286.52

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152abcd306090120150SE +/- 0.95, N = 3126.84129.44129.52125.41MIN: 84.12 / MAX: 134.23MIN: 82.93 / MAX: 135.75MIN: 83.58 / MAX: 135.06MIN: 86.22 / MAX: 129.99
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: ResNet-152abcd20406080100Min: 125.64 / Avg: 126.84 / Max: 128.72

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50abcd60120180240300SE +/- 0.18, N = 3285.74288.50288.57288.51MIN: 155.06 / MAX: 305.6MIN: 158.95 / MAX: 305.84MIN: 160.08 / MAX: 306.4MIN: 160.15 / MAX: 306.96
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-50abcd50100150200250Min: 285.52 / Avg: 285.74 / Max: 286.09

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152abcd306090120150SE +/- 0.61, N = 3126.04129.28126.00127.10MIN: 82.85 / MAX: 132.47MIN: 87.37 / MAX: 135.32MIN: 84.46 / MAX: 131.5MIN: 86.66 / MAX: 132.45
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: ResNet-152abcd20406080100Min: 125.37 / Avg: 126.04 / Max: 127.26

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152abcd306090120150SE +/- 0.24, N = 3126.55125.39127.26126.60MIN: 83.28 / MAX: 132.07MIN: 86.14 / MAX: 129.58MIN: 83.4 / MAX: 132.61MIN: 85.8 / MAX: 131.88
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: ResNet-152abcd20406080100Min: 126.18 / Avg: 126.55 / Max: 127

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152abcd306090120150SE +/- 0.41, N = 3126.58126.94123.41125.05MIN: 84.07 / MAX: 132.98MIN: 84.98 / MAX: 132.33MIN: 83.78 / MAX: 128.02MIN: 85.26 / MAX: 130.68
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: ResNet-152abcd20406080100Min: 125.76 / Avg: 126.58 / Max: 127.04

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_labcd1632486480SE +/- 0.68, N = 370.3869.6071.8071.36MIN: 61.79 / MAX: 72.15MIN: 61.72 / MAX: 70.71MIN: 63.35 / MAX: 73.09MIN: 63.42 / MAX: 72.31
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 1 - Model: Efficientnet_v2_labcd1428425670Min: 69.02 / Avg: 70.38 / Max: 71.19

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_labcd1530456075SE +/- 0.16, N = 367.4867.8666.7966.63MIN: 56.83 / MAX: 69.22MIN: 57.92 / MAX: 69.28MIN: 57.46 / MAX: 68.25MIN: 56.78 / MAX: 68.44
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 16 - Model: Efficientnet_v2_labcd1326395265Min: 67.17 / Avg: 67.48 / Max: 67.72

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_labcd1530456075SE +/- 0.50, N = 366.6568.6967.1267.59MIN: 55.99 / MAX: 68.52MIN: 58.81 / MAX: 70.38MIN: 55.88 / MAX: 68.73MIN: 58.11 / MAX: 68.86
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 32 - Model: Efficientnet_v2_labcd1326395265Min: 65.68 / Avg: 66.65 / Max: 67.36

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_labcd1530456075SE +/- 0.29, N = 367.1868.0767.3067.83MIN: 56.83 / MAX: 69.18MIN: 56.37 / MAX: 69.63MIN: 57.99 / MAX: 68.74MIN: 57.39 / MAX: 69.34
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 64 - Model: Efficientnet_v2_labcd1326395265Min: 66.63 / Avg: 67.18 / Max: 67.62

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_labcd1530456075SE +/- 0.23, N = 366.5766.2767.1267.11MIN: 55.8 / MAX: 68.27MIN: 57.1 / MAX: 67.74MIN: 56.29 / MAX: 68.56MIN: 56.28 / MAX: 68.34
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 256 - Model: Efficientnet_v2_labcd1326395265Min: 66.34 / Avg: 66.57 / Max: 67.02

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_labcd1530456075SE +/- 0.87, N = 365.9466.6366.2066.20MIN: 55.7 / MAX: 68.83MIN: 57.06 / MAX: 67.92MIN: 55.97 / MAX: 67.74MIN: 55.93 / MAX: 67.54
OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: NVIDIA CUDA GPU - Batch Size: 512 - Model: Efficientnet_v2_labcd1326395265Min: 64.37 / Avg: 65.94 / Max: 67.38