nlp-benchmarks

c6i.2xlarge NLP benchmarking on AL2023

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2402012-NE-NLPBENCHM92
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
c6i.2xlarge
February 01
  2 Hours, 25 Minutes
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):


nlp-benchmarksOpenBenchmarking.orgPhoronix Test SuiteIntel Xeon Platinum 8375C (4 Cores / 8 Threads)Amazon EC2 c6i.2xlarge (1.0 BIOS)Intel 440FX 82441FX PMC1 x 16GB DDR4-3200MT/s215GB Amazon Elastic Block StoreAmazon ElasticAmazon Linux 20236.1.61-85.141.amzn2023.x86_64 (x86_64)GCC 11.4.1 20230605xfsamazonProcessorMotherboardChipsetMemoryDiskNetworkOSKernelCompilerFile-SystemSystem LayerNlp-benchmarks PerformanceSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-amazon-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,lto --enable-multilib --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=x86-64 --with-arch_64=x86-64-v2 --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver - CPU Microcode: 0xd0003a5- Python 3.11.6- gather_data_sampling: Unknown: Dependent on hypervisor status + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT Host state unknown + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected

nlp-benchmarkspybench: Total For Average Test Timesopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUpytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpytorch: CPU - 1 - Efficientnet_v2_lpytorch: CPU - 32 - ResNet-152pytorch: CPU - 16 - ResNet-152pytorch: CPU - 32 - ResNet-50pytorch: CPU - 16 - ResNet-50pytorch: CPU - 1 - ResNet-152pytorch: CPU - 1 - ResNet-50numpy: onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUc6i.2xlarge1000179.5322.26610.596.532252.041.774.044.067.996.386.3615.8115.9610.5726.78374.992501.502492.2934.716646.698633.19202496.841.772862.038366.243918.0980312.66185.93669OpenBenchmarking.org

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Timesc6i.2xlarge2004006008001000SE +/- 0.33, N = 31000

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUc6i.2xlarge4080120160200SE +/- 0.44, N = 3179.53MIN: 100.26 / MAX: 3441. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUc6i.2xlarge510152025SE +/- 0.06, N = 322.261. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUc6i.2xlarge130260390520650SE +/- 3.28, N = 3610.59MIN: 497.95 / MAX: 643.841. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUc6i.2xlarge246810SE +/- 0.04, N = 36.531. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUc6i.2xlarge5001000150020002500SE +/- 3.74, N = 32252.04MIN: 2202.18 / MAX: 2317.241. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUc6i.2xlarge0.39830.79661.19491.59321.9915SE +/- 0.01, N = 31.771. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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: 32 - Model: Efficientnet_v2_lc6i.2xlarge0.9091.8182.7273.6364.545SE +/- 0.02, N = 34.04MIN: 3.5 / MAX: 4.36

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_lc6i.2xlarge0.91351.8272.74053.6544.5675SE +/- 0.03, N = 34.06MIN: 3.29 / MAX: 4.32

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_lc6i.2xlarge246810SE +/- 0.02, N = 37.99MIN: 6.59 / MAX: 8.31

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152c6i.2xlarge246810SE +/- 0.01, N = 36.38MIN: 3.7 / MAX: 6.57

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152c6i.2xlarge246810SE +/- 0.05, N = 36.36MIN: 5.43 / MAX: 6.61

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50c6i.2xlarge48121620SE +/- 0.17, N = 415.81MIN: 9.11 / MAX: 17.08

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50c6i.2xlarge48121620SE +/- 0.12, N = 315.96MIN: 11.65 / MAX: 17.13

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152c6i.2xlarge3691215SE +/- 0.01, N = 310.57MIN: 9.04 / MAX: 10.77

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50c6i.2xlarge612182430SE +/- 0.13, N = 326.78MIN: 13.67 / MAX: 27.8

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarkc6i.2xlarge80160240320400SE +/- 1.37, N = 3374.99

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUc6i.2xlarge5001000150020002500SE +/- 2.60, N = 32501.50MIN: 2476.861. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUc6i.2xlarge5001000150020002500SE +/- 2.42, N = 32492.29MIN: 2460.061. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUc6i.2xlarge816243240SE +/- 0.01, N = 334.72MIN: 34.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUc6i.2xlarge1122334455SE +/- 0.01, N = 346.70MIN: 46.421. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUc6i.2xlarge816243240SE +/- 0.00, N = 333.19MIN: 33.131. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUc6i.2xlarge5001000150020002500SE +/- 7.01, N = 32496.84MIN: 2465.661. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUc6i.2xlarge0.39890.79781.19671.59561.9945SE +/- 0.01317, N = 31.77286MIN: 1.731. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUc6i.2xlarge0.45860.91721.37581.83442.293SE +/- 0.00283, N = 32.03836MIN: 1.971. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUc6i.2xlarge246810SE +/- 0.08834, N = 36.24391MIN: 5.781. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUc6i.2xlarge246810SE +/- 0.01712, N = 38.09803MIN: 8.021. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUc6i.2xlarge3691215SE +/- 0.08, N = 312.66MIN: 10.81. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUc6i.2xlarge1.33582.67164.00745.34326.679SE +/- 0.03862, N = 35.93669MIN: 5.661. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl