Xeon Platinum 8380 AVX-512 Workloads

Benchmarks for a future article. 2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Ubuntu 22.10 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 2308099-NE-XEONPLATI49
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

Limit displaying results to tests within:

AV1 2 Tests
Bioinformatics 2 Tests
C/C++ Compiler Tests 5 Tests
CPU Massive 10 Tests
Creator Workloads 12 Tests
Encoding 5 Tests
Fortran Tests 4 Tests
Game Development 3 Tests
HPC - High Performance Computing 12 Tests
Machine Learning 6 Tests
Molecular Dynamics 3 Tests
MPI Benchmarks 4 Tests
Multi-Core 14 Tests
NVIDIA GPU Compute 3 Tests
Intel oneAPI 6 Tests
OpenMPI Tests 10 Tests
Python Tests 5 Tests
Renderers 2 Tests
Scientific Computing 5 Tests
Server CPU Tests 6 Tests
Video Encoding 5 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
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
0xd000390
August 06 2023
  11 Hours, 56 Minutes
0xd0003a5
August 08 2023
  15 Hours, 40 Minutes
Invert Hiding All Results Option
  13 Hours, 48 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):

Xeon Platinum 8380 AVX-512 Workloads Benchmarks for a future article. 2 x Intel Xeon Platinum 8380 testing with a Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) and ASPEED on Ubuntu 22.10 via the Phoronix Test Suite. ,,"0xd000390","0xd0003a5" Processor,,2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads),2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) Motherboard,,Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS),Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) Chipset,,Intel Ice Lake IEH,Intel Ice Lake IEH Memory,,512GB,512GB Disk,,7682GB INTEL SSDPF2KX076TZ,7682GB INTEL SSDPF2KX076TZ Graphics,,ASPEED,ASPEED Monitor,,VE228,VE228 Network,,2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP,2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP OS,,Ubuntu 22.10,Ubuntu 22.10 Kernel,,6.5.0-060500rc4daily20230804-generic (x86_64),6.5.0-rc5-phx-tues (x86_64) Desktop,,GNOME Shell 43.0,GNOME Shell 43.0 Display Server,,X Server 1.21.1.3,X Server 1.21.1.3 Vulkan,,1.3.224,1.3.224 Compiler,,GCC 12.2.0,GCC 12.2.0 File-System,,ext4,ext4 Screen Resolution,,1920x1080,1920x1080 ,,"0xd000390","0xd0003a5" "miniBUDE - Implementation: OpenMP - Input Deck: BM1 (Billion Interactions/s)",HIB,94.136,94.897 "miniBUDE - Implementation: OpenMP - Input Deck: BM2 (Billion Interactions/s)",HIB,101.076,104.048 "OpenVINO - Model: Face Detection FP16 - Device: CPU (FPS)",HIB,24.04,24.18 "OpenVINO - Model: Person Detection FP16 - Device: CPU (FPS)",HIB,13.29,13.25 "OpenVINO - Model: Person Detection FP32 - Device: CPU (FPS)",HIB,13.03,13.04 "OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (FPS)",HIB,1121.56,1117.09 "OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (FPS)",HIB,95.42,95.54 "OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (FPS)",HIB,4419.17,4442.98 "OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (FPS)",HIB,2344.97,2362.84 "OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (FPS)",HIB,251.00,255.09 "OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (FPS)",HIB,9396.52,9419.77 "OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (FPS)",HIB,2039.63,2070.72 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (FPS)",HIB,59274.06,59377.96 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (FPS)",HIB,67604.00,67754.34 "dav1d - Video Input: Chimera 1080p (FPS)",HIB,515.81,514.58 "dav1d - Video Input: Summer Nature 4K (FPS)",HIB,281.36,280.84 "Embree - Binary: Pathtracer ISPC - Model: Crown (FPS)",HIB,88.1941,83.4621 "Embree - Binary: Pathtracer ISPC - Model: Asian Dragon (FPS)",HIB,104.6844,101.0959 "SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 4K (FPS)",HIB,67.170,66.460 "SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,180.967,177.721 "SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 4K (FPS)",HIB,175.102,177.203 "SVT-HEVC - Tuning: 1 - Input: Bosphorus 4K (FPS)",HIB,10.46,10.45 "SVT-HEVC - Tuning: 7 - Input: Bosphorus 4K (FPS)",HIB,138.75,138.49 "SVT-HEVC - Tuning: 10 - Input: Bosphorus 4K (FPS)",HIB,184.38,182.74 "VP9 libvpx Encoding - Speed: Speed 5 - Input: Bosphorus 4K (FPS)",HIB,12.63,12.33 "VVenC - Video Input: Bosphorus 4K - Video Preset: Fast (FPS)",HIB,5.722,5.705 "VVenC - Video Input: Bosphorus 4K - Video Preset: Faster (FPS)",HIB,10.364,10.415 "simdjson - Throughput Test: Kostya (GB/s)",HIB,2.61,2.87 "simdjson - Throughput Test: TopTweet (GB/s)",HIB,5.60,5.75 "simdjson - Throughput Test: LargeRandom (GB/s)",HIB,0.85,0.96 "simdjson - Throughput Test: PartialTweets (GB/s)",HIB,4.62,4.77 "simdjson - Throughput Test: DistinctUserID (GB/s)",HIB,5.52,5.71 "miniBUDE - Implementation: OpenMP - Input Deck: BM1 (GFInst/s)",HIB,2353.389,2372.418 "miniBUDE - Implementation: OpenMP - Input Deck: BM2 (GFInst/s)",HIB,2526.887,2601.212 "HeFFTe - Highly Efficient FFT for Exascale - Test: c2c - Backend: FFTW - Precision: float - X Y Z: 128 (GFLOP/s)",HIB,154.731,159.100 "HeFFTe - Highly Efficient FFT for Exascale - Test: c2c - Backend: FFTW - Precision: float - X Y Z: 256 (GFLOP/s)",HIB,101.977,102.920 "HeFFTe - Highly Efficient FFT for Exascale - Test: r2c - Backend: FFTW - Precision: float - X Y Z: 128 (GFLOP/s)",HIB,195.199,198.869 "HeFFTe - Highly Efficient FFT for Exascale - Test: r2c - Backend: FFTW - Precision: float - X Y Z: 256 (GFLOP/s)",HIB,224.417,226.783 "HeFFTe - Highly Efficient FFT for Exascale - Test: c2c - Backend: FFTW - Precision: double - X Y Z: 128 (GFLOP/s)",HIB,93.0906,93.9207 "HeFFTe - Highly Efficient FFT for Exascale - Test: c2c - Backend: FFTW - Precision: double - X Y Z: 256 (GFLOP/s)",HIB,46.3516,46.9833 "HeFFTe - Highly Efficient FFT for Exascale - Test: r2c - Backend: FFTW - Precision: double - X Y Z: 128 (GFLOP/s)",HIB,144.942,153.790 "HeFFTe - Highly Efficient FFT for Exascale - Test: r2c - Backend: FFTW - Precision: double - X Y Z: 256 (GFLOP/s)",HIB,93.7474,94.8614 "libxsmm - M N K: 128 (GFLOPS/s)",HIB,1941.1,1978.9 "libxsmm - M N K: 256 (GFLOPS/s)",HIB,594.6,600.2 "libxsmm - M N K: 32 (GFLOPS/s)",HIB,604.7,609.2 "libxsmm - M N K: 64 (GFLOPS/s)",HIB,1098.8,1177.1 "Intel Open Image Denoise - Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only (Images / Sec)",HIB,3.03,3.03 "Intel Open Image Denoise - Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only (Images / Sec)",HIB,1.46,1.46 "TensorFlow - Device: CPU - Batch Size: 256 - Model: AlexNet (images/sec)",HIB,723.27,781.25 "TensorFlow - Device: CPU - Batch Size: 512 - Model: AlexNet (images/sec)",HIB,760.15,839.41 "TensorFlow - Device: CPU - Batch Size: 256 - Model: GoogLeNet (images/sec)",HIB,309.63,321.72 "TensorFlow - Device: CPU - Batch Size: 256 - Model: ResNet-50 (images/sec)",HIB,83.89,86.93 "TensorFlow - Device: CPU - Batch Size: 512 - Model: GoogLeNet (images/sec)",HIB,317.27,323.79 "TensorFlow - Device: CPU - Batch Size: 512 - Model: ResNet-50 (images/sec)",HIB,85.97,84.84 "ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,180.163,190.570 "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,11.6605,11.1539 "ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,16.7110,16.3098 "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,696.725,664.537 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,9.08067,8.59908 "ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,39.1157,38.7185 "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,221.020,216.481 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inferences/sec)",HIB,158.355,158.014 "OpenVKL - Benchmark: vklBenchmark ISPC (Items / Sec)",HIB,912,856 "OSPRay - Benchmark: particle_volume/ao/real_time (Items/sec)",HIB,24.7473,16.4611 "OSPRay - Benchmark: particle_volume/scivis/real_time (Items/sec)",HIB,24.9506,16.3849 "OSPRay - Benchmark: particle_volume/pathtracer/real_time (Items/sec)",HIB,150.281,136.853 "OSPRay - Benchmark: gravity_spheres_volume/dim_512/ao/real_time (Items/sec)",HIB,21.0761,18.8862 "OSPRay - Benchmark: gravity_spheres_volume/dim_512/scivis/real_time (Items/sec)",HIB,20.5780,18.4626 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,72.0674,71.8868 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,2301.1554,2068.3047 "Neural Magic DeepSparse - Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,922.9302,930.7506 "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,230.0525,231.4277 "Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,1006.3407,1013.8215 "Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,7633.2598,7092.5030 "Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,422.1167,412.0531 "Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,98.3394,94.2573 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,1005.5843,987.5452 "Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,426.9495,398.7153 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,644.4430,620.2548 "Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,84.0181,83.2041 "Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,1051.7868,869.0393 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,307.8729,293.1241 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,72.1788,71.5436 "Cpuminer-Opt - Algorithm: Magi (kH/s)",HIB,2309.47,2308.66 "Cpuminer-Opt - Algorithm: x25x (kH/s)",HIB,2659.17,2659.55 "Cpuminer-Opt - Algorithm: scrypt (kH/s)",HIB,2319.31,2321.74 "Cpuminer-Opt - Algorithm: Deepcoin (kH/s)",HIB,64677,64897 "Cpuminer-Opt - Algorithm: Blake-2 S (kH/s)",HIB,4462327,4466653 "Cpuminer-Opt - Algorithm: Garlicoin (kH/s)",HIB,29203,22086.25 "Cpuminer-Opt - Algorithm: Skeincoin (kH/s)",HIB,613333,617130 "Cpuminer-Opt - Algorithm: Myriad-Groestl (kH/s)",HIB,43127,43450 "Cpuminer-Opt - Algorithm: LBC, LBRY Credits (kH/s)",HIB,421660,423130 "Cpuminer-Opt - Algorithm: Quad SHA-256, Pyrite (kH/s)",HIB,921730,926277 "Cpuminer-Opt - Algorithm: Triple SHA-256, Onecoin (kH/s)",HIB,1332237,1333117 "Laghos - Test: Triple Point Problem (Major Kernels Rate)",HIB,256.27,256.87 "Laghos - Test: Sedov Blast Wave, ube_922_hex.mesh (Major Kernels Rate)",HIB,385.89,386.08 "Palabos - Grid Size: 100 (Mega Site Updates/sec)",HIB,312.195,312.530 "Palabos - Grid Size: 400 (Mega Site Updates/sec)",HIB,388.476,393.844 "Palabos - Grid Size: 500 (Mega Site Updates/sec)",HIB,413.207,417.483 "GROMACS - Implementation: MPI CPU - Input: water_GMX50_bare (Ns/Day)",HIB,9.234,9.094 "ONNX Runtime - Model: GPT-2 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,5.54783,5.28095 "ONNX Runtime - Model: yolov4 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,85.7987,89.8299 "ONNX Runtime - Model: bertsquad-12 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,59.8415,61.5091 "ONNX Runtime - Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,1.43407,1.51029 "ONNX Runtime - Model: fcn-resnet101-11 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,110.323,117.545 "ONNX Runtime - Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,25.5687,25.8601 "ONNX Runtime - Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,4.52403,4.62085 "ONNX Runtime - Model: super-resolution-10 - Device: CPU - Executor: Standard (Inference Time Cost (ms))",LIB,6.31428,6.71968 "oneDNN - Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,2.59271,2.57437 "oneDNN - Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,2.06936,2.06967 "oneDNN - Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,3.90360,3.91322 "oneDNN - Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,3.62526,3.62266 "oneDNN - Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,832.452,816.508 "oneDNN - Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU (ms)",LIB,524.381,521.742 "OpenVINO - Model: Face Detection FP16 - Device: CPU (ms)",LIB,827.51,823.09 "OpenVINO - Model: Person Detection FP16 - Device: CPU (ms)",LIB,1490.76,1496.19 "OpenVINO - Model: Person Detection FP32 - Device: CPU (ms)",LIB,1517.69,1519.84 "OpenVINO - Model: Vehicle Detection FP16 - Device: CPU (ms)",LIB,17.80,17.87 "OpenVINO - Model: Face Detection FP16-INT8 - Device: CPU (ms)",LIB,209.31,209.02 "OpenVINO - Model: Vehicle Detection FP16-INT8 - Device: CPU (ms)",LIB,4.51,4.49 "OpenVINO - Model: Weld Porosity Detection FP16 - Device: CPU (ms)",LIB,33.89,33.63 "OpenVINO - Model: Machine Translation EN To DE FP16 - Device: CPU (ms)",LIB,79.47,78.18 "OpenVINO - Model: Weld Porosity Detection FP16-INT8 - Device: CPU (ms)",LIB,8.50,8.48 "OpenVINO - Model: Person Vehicle Bike Detection FP16 - Device: CPU (ms)",LIB,9.77,9.63 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU (ms)",LIB,1.33,1.33 "OpenVINO - Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU (ms)",LIB,1.16,1.16 "NCNN - Target: CPU - Model: mobilenet (ms)",LIB,15.46,15.66 "NCNN - Target: CPU-v2-v2 - Model: mobilenet-v2 (ms)",LIB,8.03,7.96 "NCNN - Target: CPU-v3-v3 - Model: mobilenet-v3 (ms)",LIB,8.88,8.76 "NCNN - Target: CPU - Model: shufflenet-v2 (ms)",LIB,9.89,9.76 "NCNN - Target: CPU - Model: mnasnet (ms)",LIB,7.57,7.41 "NCNN - Target: CPU - Model: efficientnet-b0 (ms)",LIB,11.62,11.71 "NCNN - Target: CPU - Model: blazeface (ms)",LIB,4.35,4.54 "NCNN - Target: CPU - Model: googlenet (ms)",LIB,15.36,16.58 "NCNN - Target: CPU - Model: vgg16 (ms)",LIB,23.86,25.71 "NCNN - Target: CPU - Model: resnet18 (ms)",LIB,8.97,9.42 "NCNN - Target: CPU - Model: alexnet (ms)",LIB,5.39,5.46 "NCNN - Target: CPU - Model: resnet50 (ms)",LIB,17.15,18.51 "NCNN - Target: CPU - Model: yolov4-tiny (ms)",LIB,23.71,24.10 "NCNN - Target: CPU - Model: squeezenet_ssd (ms)",LIB,15.34,16.10 "NCNN - Target: CPU - Model: regnety_400m (ms)",LIB,45.54,38.85 "NCNN - Target: CPU - Model: vision_transformer (ms)",LIB,46.92,45.23 "NCNN - Target: CPU - Model: FastestDet (ms)",LIB,10.20,9.71 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,551.1195,553.2682 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,17.3504,19.3090 "Neural Magic DeepSparse - Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,43.3033,42.9405 "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,173.7945,172.5579 "Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,39.6954,39.4131 "Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,5.2210,5.6210 "Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,94.6126,96.9429 "Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,405.9662,421.7544 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,39.7308,40.4508 "Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,93.5399,100.1856 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,62.0099,64.4439 "Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,474.6917,478.8510 "Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,37.9943,45.9597 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,129.8095,136.1780 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,551.8180,555.0876 "CloverLeaf - Lagrangian-Eulerian Hydrodynamics (sec)",LIB,12.04,11.98 "Xcompact3d Incompact3d - Input: input.i3d 193 Cells Per Direction (sec)",LIB,11.0240278,11.0041968 "Remhos - Test: Sample Remap Example (sec)",LIB,12.245,12.401 "SPECFEM3D - Model: Mount St. Helens (sec)",LIB,13.148692362,12.948759795 "SPECFEM3D - Model: Layered Halfspace (sec)",LIB,29.497987898,29.373606551 "SPECFEM3D - Model: Tomographic Model (sec)",LIB,14.574192022,14.145999546 "SPECFEM3D - Model: Homogeneous Halfspace (sec)",LIB,18.022236470,17.751628972 "SPECFEM3D - Model: Water-layered Halfspace (sec)",LIB,31.146951238,31.381798528 "Timed MrBayes Analysis - Primate Phylogeny Analysis (sec)",LIB,166.528,165.419 "Blender - Blend File: BMW27 - Compute: CPU-Only (sec)",LIB,23.83,23.72 "Blender - Blend File: Fishy Cat - Compute: CPU-Only (sec)",LIB,30.74,30.90 "QMCPACK - Input: Li2_STO_ae (Execution Time - sec)",LIB,124.23,123.26 "QMCPACK - Input: simple-H2O (Execution Time - sec)",LIB,39.555,41.246 "QMCPACK - Input: FeCO6_b3lyp_gms (Execution Time - sec)",LIB,147.51,178.19 "QMCPACK - Input: FeCO6_b3lyp_gms (Execution Time - sec)",LIB,268.56,263.23