pyt

AMD EPYC 9654 96-Core testing with a AMD Titanite_4G (RTI1007B BIOS) and ASPEED on Ubuntu 23.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2311183-NE-PYT49584300&grr&sro.

pytProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen Resolutionabcd2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads)AMD Titanite_4G (RTI1007B BIOS)AMD Device 14a41520GB3201GB Micron_7450_MTFDKCC3T2TFSASPEEDBroadcom NetXtreme BCM5720 PCIeUbuntu 23.106.6.0-rc5-phx-patched (x86_64)GNOME Shell 45.0X Server 1.21.1.7GCC 13.2.0ext41920x1200AMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads)768GBOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseProcessor Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10113ePython Details- Python 3.11.6Security 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

pytpytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 256 - Efficientnet_v2_lpytorch: CPU - 512 - Efficientnet_v2_lpytorch: CPU - 64 - Efficientnet_v2_lpytorch: CPU - 512 - ResNet-152pytorch: CPU - 256 - ResNet-152pytorch: CPU - 64 - ResNet-152pytorch: CPU - 32 - ResNet-152pytorch: CPU - 16 - ResNet-152pytorch: CPU - 1 - Efficientnet_v2_lpytorch: CPU - 1 - ResNet-152pytorch: CPU - 16 - ResNet-50pytorch: CPU - 256 - ResNet-50pytorch: CPU - 64 - ResNet-50pytorch: CPU - 32 - ResNet-50pytorch: CPU - 512 - ResNet-50pytorch: CPU - 1 - ResNet-50abcd1.291.298.718.978.949.349.246.7510.2820.2220.5520.4621.7721.3721.916.366.446.346.406.4116.4816.4516.4416.1216.3810.8918.9239.8739.4240.0639.8239.6946.616.386.3716.4616.1415.8416.0516.0811.1117.8339.8039.7539.9639.8339.9346.716.366.396.406.386.3715.8916.5716.5915.8916.0110.9618.6540.3840.2339.7739.5439.3546.45OpenBenchmarking.org

PyTorch

Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_labcd2468101.296.366.386.36MIN: 0.48 / MAX: 2.37MIN: 5.91 / MAX: 6.47MIN: 5.17 / MAX: 6.51MIN: 5.94 / MAX: 6.48

PyTorch

Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_labcd2468101.296.446.376.39MIN: 0.62 / MAX: 2.39MIN: 5.99 / MAX: 6.57MIN: 5.95 / MAX: 6.52MIN: 4.97 / MAX: 6.52

PyTorch

Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_lbd2468106.346.40MIN: 5.84 / MAX: 6.47MIN: 6 / MAX: 6.53

PyTorch

Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_lbd2468106.406.38MIN: 5.88 / MAX: 6.53MIN: 5.97 / MAX: 6.5

PyTorch

Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lbd2468106.416.37MIN: 5.98 / MAX: 6.55MIN: 5.86 / MAX: 6.49

PyTorch

Device: CPU - Batch Size: 512 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-152abcd481216208.7116.4816.4615.89MIN: 8.58 / MAX: 8.83MIN: 16.26 / MAX: 16.64MIN: 16.27 / MAX: 16.61MIN: 15.72 / MAX: 16.05

PyTorch

Device: CPU - Batch Size: 256 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-152abcd481216208.9716.4516.1416.57MIN: 5.15 / MAX: 9.12MIN: 16.26 / MAX: 16.62MIN: 15.96 / MAX: 16.34MIN: 16.4 / MAX: 16.73

PyTorch

Device: CPU - Batch Size: 64 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152abcd481216208.9416.4415.8416.59MIN: 4.61 / MAX: 9.21MIN: 16.27 / MAX: 16.62MIN: 15.67 / MAX: 16MIN: 16.4 / MAX: 16.74

PyTorch

Device: CPU - Batch Size: 32 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152abcd481216209.3416.1216.0515.89MIN: 5.1 / MAX: 9.48MIN: 15.97 / MAX: 16.29MIN: 15.91 / MAX: 16.29MIN: 15.7 / MAX: 16.11

PyTorch

Device: CPU - Batch Size: 16 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152abcd481216209.2416.3816.0816.01MIN: 6.47 / MAX: 9.41MIN: 16.2 / MAX: 16.56MIN: 15.91 / MAX: 16.23MIN: 15.87 / MAX: 16.17

PyTorch

Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_labcd36912156.7510.8911.1110.96MIN: 4.17 / MAX: 6.89MIN: 10.79 / MAX: 10.98MIN: 11.02 / MAX: 11.2MIN: 10.88 / MAX: 11.02

PyTorch

Device: CPU - Batch Size: 1 - Model: ResNet-152

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152abcd51015202510.2818.9217.8318.65MIN: 5.05 / MAX: 10.64MIN: 10.58 / MAX: 19.1MIN: 17.67 / MAX: 17.98MIN: 18.45 / MAX: 18.9

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50abcd91827364520.2239.8739.8040.38MIN: 11.34 / MAX: 20.76MIN: 38.37 / MAX: 40.84MIN: 38.39 / MAX: 40.71MIN: 39.31 / MAX: 41.34

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 256 - Model: ResNet-50abcd91827364520.5539.4239.7540.23MIN: 12.2 / MAX: 21.39MIN: 38.56 / MAX: 40.13MIN: 38.53 / MAX: 40.65MIN: 39.26 / MAX: 41.13

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50abcd91827364520.4640.0639.9639.77MIN: 12.21 / MAX: 21.36MIN: 39.17 / MAX: 40.95MIN: 38.88 / MAX: 40.88MIN: 38.66 / MAX: 40.81

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50abcd91827364521.7739.8239.8339.54MIN: 18.59 / MAX: 22.39MIN: 38.85 / MAX: 40.77MIN: 39.1 / MAX: 40.71MIN: 38.66 / MAX: 40.21

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 512 - Model: ResNet-50abcd91827364521.3739.6939.9339.35MIN: 20.51 / MAX: 21.86MIN: 38.5 / MAX: 40.43MIN: 38.89 / MAX: 40.82MIN: 38.36 / MAX: 40.29

PyTorch

Device: CPU - Batch Size: 1 - Model: ResNet-50

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50abcd112233445521.9146.6146.7146.45MIN: 12.38 / MAX: 23.84MIN: 41.78 / MAX: 47.84MIN: 45.82 / MAX: 47.64MIN: 45.7 / MAX: 47.37

Phoronix Test Suite v10.8.5