nlp-benchmarks

AWS EC2 Amazon Linux 2023 Benchmarking

HTML result view exported from: https://openbenchmarking.org/result/2402094-NE-2402012NE30&rdt&grs.

nlp-benchmarksProcessorMotherboardChipsetMemoryDiskNetworkOSKernelCompilerFile-SystemSystem Layerc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlargeIntel 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 20230605xfsamazonIntel Xeon Platinum 8488C (4 Cores / 8 Threads)Amazon EC2 m7i-flex.2xlarge (1.0 BIOS)1 x 32GB 4800MT/s6.1.72-96.166.amzn2023.x86_64 (x86_64)AMD EPYC 9R14 (8 Cores)Amazon EC2 c7a.2xlarge (1.0 BIOS)1 x 16GB 4800MT/sAMD EPYC 9R14 (4 Cores)Amazon EC2 r7a.xlarge (1.0 BIOS)1 x 32GB 4800MT/sOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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 Processor Details- c6i.2xlarge: CPU Microcode: 0xd0003a5- m7i-flex.2xlarge: CPU Microcode: 0x2b000571- c7a.2xlarge: CPU Microcode: 0xa10113e- r7a.xlarge: CPU Microcode: 0xa10113ePython Details- Python 3.11.6Security Details- c6i.2xlarge: 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 - m7i-flex.2xlarge: 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: 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 - c7a.2xlarge: 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 no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected - r7a.xlarge: 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 no microcode + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: disabled RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

nlp-benchmarksopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUonednn: Deconvolution Batch shapes_1d - bf16bf16bf16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUopenvino: Machine Translation EN To DE FP16 - CPUpytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUpytorch: CPU - 32 - ResNet-152pytorch: CPU - 16 - ResNet-152onednn: Deconvolution Batch shapes_3d - bf16bf16bf16 - CPUonednn: Convolution Batch Shapes Auto - bf16bf16bf16 - CPUpytorch: CPU - 16 - ResNet-50onednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - u8s8f32 - CPUonednn: Recurrent Neural Network Inference - f32 - CPUpytorch: CPU - 1 - ResNet-152pytorch: CPU - 1 - ResNet-50numpy: pytorch: CPU - 1 - Efficientnet_v2_lonednn: Convolution Batch Shapes Auto - f32 - CPUpybench: Total For Average Test Timesonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUpytorch: CPU - 32 - ResNet-50c6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge1.772252.046.5346.6986179.53610.5912.66181.7728622.264.044.062.038366.386.3634.716633.192015.968.098032501.502492.292496.8410.5726.78374.997.995.9366910006.2439115.818.43474.4616.571.7635074.20241.218.100071.00326953.875.475.381.0163277.557.363.110753.6899318.847.948782318.312389.642382.4612.1029.89438.258.995.842617367.1946218.345.16774.239.766.9020073.34409.785.014371.2640554.518.718.751.0942913.0312.953.123393.2824531.895.103301478.511480.931482.3520.0050.16590.1011.747.351018877.7461931.292.62764.304.913.731864.98408.029.854412.5298230.775.675.662.180297.687.686.259075.4078419.3510.16792862.862857.772856.8413.1933.39595.018.448.226918877.3873219.32OpenBenchmarking.org

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge246810SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.778.435.162.621. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge5001000150020002500SE +/- 3.74, N = 3SE +/- 5.97, N = 3SE +/- 0.28, N = 3SE +/- 0.15, N = 32252.04474.46774.23764.30MIN: 2202.18 / MAX: 2317.24MIN: 427.39 / MAX: 558.54MIN: 767.78 / MAX: 795.49MIN: 761.82 / MAX: 783.231. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge48121620SE +/- 0.04, N = 3SE +/- 0.16, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 36.5316.579.764.901. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge1122334455SE +/- 0.01032, N = 3SE +/- 0.00827, N = 3SE +/- 0.00810, N = 3SE +/- 0.02961, N = 346.698601.763506.9020013.73180MIN: 46.42MIN: 13.511. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge4080120160200SE +/- 0.44, N = 3SE +/- 0.25, N = 3SE +/- 0.02, N = 3SE +/- 0.40, N = 3179.5374.2073.3464.98MIN: 100.26 / MAX: 344MIN: 34.84 / MAX: 96.18MIN: 65.17 / MAX: 80.62MIN: 61.57 / MAX: 90.411. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge130260390520650SE +/- 3.28, N = 3SE +/- 2.35, N = 3SE +/- 0.07, N = 3SE +/- 0.14, N = 3610.59241.21409.78408.02MIN: 497.95 / MAX: 643.84MIN: 91.81 / MAX: 374.94MIN: 407.35 / MAX: 424.19MIN: 406.22 / MAX: 426.041. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge3691215SE +/- 0.07954, N = 3SE +/- 0.01302, N = 3SE +/- 0.00229, N = 3SE +/- 0.00467, N = 312.661808.100075.014379.85441MIN: 10.8MIN: 6.7MIN: 4.93MIN: 9.751. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge0.56921.13841.70762.27682.846SE +/- 0.013170, N = 3SE +/- 0.011545, N = 4SE +/- 0.004187, N = 3SE +/- 0.006412, N = 31.7728601.0032691.2640502.529820MIN: 1.73MIN: 0.84MIN: 1.25MIN: 2.51. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge1224364860SE +/- 0.06, N = 3SE +/- 0.19, N = 3SE +/- 0.02, N = 3SE +/- 0.18, N = 322.2653.8754.5130.771. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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_lc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 34.045.478.715.67MIN: 3.5 / MAX: 4.36MIN: 2.31 / MAX: 6.19MIN: 5.53 / MAX: 8.82MIN: 4.37 / MAX: 5.73

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_lc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge246810SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34.065.388.755.66MIN: 3.29 / MAX: 4.32MIN: 2.12 / MAX: 6.08MIN: 5.72 / MAX: 8.84MIN: 4.27 / MAX: 5.72

oneDNN

Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge0.49060.98121.47181.96242.453SE +/- 0.002826, N = 3SE +/- 0.013619, N = 15SE +/- 0.002971, N = 3SE +/- 0.000469, N = 32.0383601.0163271.0942902.180290MIN: 1.97MIN: 0.79MIN: 1.08MIN: 2.151. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152c6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge3691215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 36.387.5513.037.68MIN: 3.7 / MAX: 6.57MIN: 2.93 / MAX: 8.62MIN: 10.5 / MAX: 13.2MIN: 6.31 / MAX: 7.76

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152c6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge3691215SE +/- 0.05, N = 3SE +/- 0.08, N = 5SE +/- 0.09, N = 3SE +/- 0.02, N = 36.367.3612.957.68MIN: 5.43 / MAX: 6.61MIN: 2.24 / MAX: 8.66MIN: 4.2 / MAX: 13.21MIN: 6.45 / MAX: 7.76

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge816243240SE +/- 0.00790, N = 3SE +/- 0.01261, N = 3SE +/- 0.00414, N = 3SE +/- 0.01228, N = 334.716603.110753.123396.25907MIN: 34.6MIN: 6.181. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge816243240SE +/- 0.00337, N = 3SE +/- 0.03984, N = 3SE +/- 0.00275, N = 3SE +/- 0.02244, N = 333.192003.689933.282455.40784MIN: 33.13MIN: 5.321. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50c6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge714212835SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.24, N = 3SE +/- 0.18, N = 315.9618.8431.8919.35MIN: 11.65 / MAX: 17.13MIN: 4.37 / MAX: 21.77MIN: 23.54 / MAX: 32.58MIN: 15.18 / MAX: 19.82

oneDNN

Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge3691215SE +/- 0.01712, N = 3SE +/- 0.08711, N = 3SE +/- 0.00261, N = 3SE +/- 0.01406, N = 38.098037.948785.1033010.16790MIN: 8.02MIN: 6.79MIN: 5.05MIN: 10.111. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge6001200180024003000SE +/- 2.60, N = 3SE +/- 15.72, N = 3SE +/- 1.00, N = 3SE +/- 3.75, N = 32501.502318.311478.512862.86MIN: 2476.86MIN: 2205.71MIN: 1472.49MIN: 2849.871. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge6001200180024003000SE +/- 2.42, N = 3SE +/- 24.80, N = 3SE +/- 2.09, N = 3SE +/- 1.65, N = 32492.292389.641480.932857.77MIN: 2460.06MIN: 2260.99MIN: 1474.24MIN: 2848.471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge6001200180024003000SE +/- 7.01, N = 3SE +/- 26.45, N = 4SE +/- 1.52, N = 3SE +/- 2.56, N = 32496.842382.461482.352856.84MIN: 2465.66MIN: 2219.69MIN: 1476.16MIN: 2845.851. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152c6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge510152025SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 310.5712.1020.0013.19MIN: 9.04 / MAX: 10.77MIN: 2.89 / MAX: 13.92MIN: 15.6 / MAX: 20.36MIN: 10.96 / MAX: 13.33

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50c6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge1122334455SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.32, N = 3SE +/- 0.04, N = 326.7829.8950.1633.39MIN: 13.67 / MAX: 27.8MIN: 7.96 / MAX: 34.56MIN: 33.27 / MAX: 51.43MIN: 24.56 / MAX: 33.78

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmarkc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge130260390520650SE +/- 1.37, N = 3SE +/- 3.53, N = 3SE +/- 1.02, N = 3SE +/- 0.90, N = 3374.99438.25590.10595.01

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_lc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge3691215SE +/- 0.02, N = 3SE +/- 0.09, N = 12SE +/- 0.02, N = 3SE +/- 0.01, N = 37.998.9911.748.44MIN: 6.59 / MAX: 8.31MIN: 3.08 / MAX: 10.39MIN: 8.95 / MAX: 11.9MIN: 2.94 / MAX: 8.53

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge246810SE +/- 0.03862, N = 3SE +/- 0.02435, N = 3SE +/- 0.01338, N = 3SE +/- 0.00015, N = 35.936695.842617.351018.22691MIN: 5.66MIN: 5MIN: 7.22MIN: 8.11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Timesc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge2004006008001000SE +/- 0.33, N = 3SE +/- 3.18, N = 3SE +/- 0.67, N = 3SE +/- 1.33, N = 31000736887887

oneDNN

Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.3Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUc6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge246810SE +/- 0.08834, N = 3SE +/- 0.03815, N = 3SE +/- 0.01540, N = 3SE +/- 0.01020, N = 36.243917.194627.746197.38732MIN: 5.78MIN: 6.66MIN: 7.55MIN: 7.271. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl

PyTorch

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

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50c6i.2xlargem7i-flex.2xlargec7a.2xlarger7a.xlarge714212835SE +/- 0.17, N = 4SE +/- 0.29, N = 15SE +/- 0.42, N = 15SE +/- 0.15, N = 1015.8118.3431.2919.32MIN: 9.11 / MAX: 17.08MIN: 4.11 / MAX: 22.15MIN: 20.73 / MAX: 33.27MIN: 13.74 / MAX: 19.98

Phoronix Test Suite v10.8.5