zn

2 x AMD EPYC 7773X 64-Core testing with a AMD DAYTONA_X (RYM1009B BIOS) and ASPEED on Ubuntu 22.04 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 2305011-NE-ZN838339286
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:

Timed Code Compilation 6 Tests
C/C++ Compiler Tests 8 Tests
CPU Massive 10 Tests
Creator Workloads 10 Tests
Cryptography 2 Tests
Database Test Suite 3 Tests
Encoding 4 Tests
Fortran Tests 2 Tests
Game Development 4 Tests
HPC - High Performance Computing 3 Tests
Common Kernel Benchmarks 3 Tests
Machine Learning 2 Tests
Multi-Core 14 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 2 Tests
Programmer / Developer System Benchmarks 6 Tests
Python Tests 8 Tests
Server 6 Tests
Server CPU Tests 6 Tests
Video Encoding 3 Tests
Common Workstation Benchmarks 2 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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
a
April 30 2023
  4 Hours, 57 Minutes
b
April 30 2023
  4 Hours, 22 Minutes
c
April 30 2023
  4 Hours, 54 Minutes
Invert Hiding All Results Option
  4 Hours, 44 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):

zn 2 x AMD EPYC 7773X 64-Core testing with a AMD DAYTONA_X (RYM1009B BIOS) and ASPEED on Ubuntu 22.04 via the Phoronix Test Suite. ,,"a","b","c" Processor,,2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads),2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads),2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads) Motherboard,,AMD DAYTONA_X (RYM1009B BIOS),AMD DAYTONA_X (RYM1009B BIOS),AMD DAYTONA_X (RYM1009B BIOS) Chipset,,AMD Starship/Matisse,AMD Starship/Matisse,AMD Starship/Matisse Memory,,512GB,512GB,512GB Disk,,3841GB Micron_9300_MTFDHAL3T8TDP,3841GB Micron_9300_MTFDHAL3T8TDP,3841GB Micron_9300_MTFDHAL3T8TDP Graphics,,ASPEED,ASPEED,ASPEED Monitor,,VE228,VE228,VE228 Network,,2 x Mellanox MT27710,2 x Mellanox MT27710,2 x Mellanox MT27710 OS,,Ubuntu 22.04,Ubuntu 22.04,Ubuntu 22.04 Kernel,,5.15.0-47-generic (x86_64),5.15.0-47-generic (x86_64),5.15.0-47-generic (x86_64) Desktop,,GNOME Shell 42.4,GNOME Shell 42.4,GNOME Shell 42.4 Display Server,,X Server 1.21.1.3,X Server 1.21.1.3,X Server 1.21.1.3 Vulkan,,1.2.204,1.2.204,1.2.204 Compiler,,GCC 11.2.0,GCC 11.2.0,GCC 11.2.0 File-System,,ext4,ext4,ext4 Screen Resolution,,1920x1080,1920x1080,1920x1080 ,,"a","b","c" "TensorFlow - Device: CPU - Batch Size: 512 - Model: ResNet-50 (images/sec)",HIB,16.59,16.67,16.34 "TensorFlow - Device: CPU - Batch Size: 256 - Model: ResNet-50 (images/sec)",HIB,15.04,15.12,14.77 "BRL-CAD - VGR Performance Metric (VGR Performance Metric)",HIB,3089503,,3047016 "PETSc - Test: Streams (MB/s)",HIB,180447.2727,251700.4996,250852.5482 "TensorFlow - Device: CPU - Batch Size: 64 - Model: ResNet-50 (images/sec)",HIB,13.76,13.74,13.59 "OpenVKL - Benchmark: vklBenchmark ISPC (Items / Sec)",HIB,489,539,521 "OpenVKL - Benchmark: vklBenchmark Scalar (Items / Sec)",HIB,337,381,363 "TensorFlow - Device: CPU - Batch Size: 32 - Model: ResNet-50 (images/sec)",HIB,13.24,13.37,13.1 "ClickHouse - 100M Rows Hits Dataset, Third Run (Queries/min, Geo Mean)",HIB,274.77,404.69,410.26 "ClickHouse - 100M Rows Hits Dataset, Second Run (Queries/min, Geo Mean)",HIB,273.45,413.04,403.80 "ClickHouse - 100M Rows Hits Dataset, First Run / Cold Cache (Queries/min, Geo Mean)",HIB,269.19,401.11,398.91 "Timed LLVM Compilation - Build System: Unix Makefiles (sec)",LIB,228.853,210.169,211.16 "Timed Linux Kernel Compilation - Build: allmodconfig (sec)",LIB,285.347,160.583,160.786 "OpenSSL - Algorithm: SHA256 (byte/s)",HIB,152584380080,152693644050,152508733130 "OpenSSL - Algorithm: AES-256-GCM (byte/s)",HIB,424974892240,425089252010,424554074930 "OpenSSL - Algorithm: AES-128-GCM (byte/s)",HIB,464927934750,464448030860,464259772140 "OpenSSL - Algorithm: ChaCha20 (byte/s)",HIB,434799000510,435044716540,434402920310 "OpenSSL - Algorithm: SHA512 (byte/s)",HIB,48236952220,48315690210,48197587440 "OpenSSL - Algorithm: ChaCha20-Poly1305 (byte/s)",HIB,285698755410,285959794140,286255847010 "TensorFlow - Device: CPU - Batch Size: 16 - Model: ResNet-50 (images/sec)",HIB,12.54,12.48,12.33 "Blender - Blend File: Barbershop - Compute: CPU-Only (sec)",LIB,136.18,136.92,136.8 "Timed Node.js Compilation - Time To Compile (sec)",LIB,132.531,115.742,114.588 "Timed LLVM Compilation - Build System: Ninja (sec)",LIB,132.966,113.357,112.52 "VVenC - Video Input: Bosphorus 4K - Video Preset: Fast (FPS)",HIB,5.509,5.57,5.577 "CockroachDB - Workload: KV, 50% Reads - Concurrency: 512 (ops/s)",HIB,68395.4,56432.6,68164.4 "CockroachDB - Workload: KV, 10% Reads - Concurrency: 512 (ops/s)",HIB,50885.4,52529.5,46271.6 "CockroachDB - Workload: KV, 60% Reads - Concurrency: 512 (ops/s)",HIB,60903.7,62154.2,73656.2 "CockroachDB - Workload: KV, 95% Reads - Concurrency: 512 (ops/s)",HIB,72445,90237.5,86788.8 "CockroachDB - Workload: KV, 10% Reads - Concurrency: 256 (ops/s)",HIB,50683.8,47146.4,50241 "CockroachDB - Workload: KV, 60% Reads - Concurrency: 256 (ops/s)",HIB,72158.1,63269,73004.2 "CockroachDB - Workload: KV, 95% Reads - Concurrency: 256 (ops/s)",HIB,88008.4,74468.4,73252.3 "CockroachDB - Workload: KV, 50% Reads - Concurrency: 256 (ops/s)",HIB,58777.4,68400,57909.1 "CockroachDB - Workload: KV, 50% Reads - Concurrency: 128 (ops/s)",HIB,65133.4,66115.6,57115.1 "CockroachDB - Workload: KV, 60% Reads - Concurrency: 128 (ops/s)",HIB,70322.4,72193.2,69343.2 "CockroachDB - Workload: KV, 10% Reads - Concurrency: 128 (ops/s)",HIB,49533.1,49454.9,48767.1 "CockroachDB - Workload: KV, 95% Reads - Concurrency: 128 (ops/s)",HIB,88685.5,88959.8,87476.4 "Timed Godot Game Engine Compilation - Time To Compile (sec)",LIB,102.825,98.419,98.299 "CockroachDB - Workload: MoVR - Concurrency: 128 (ops/s)",HIB,754.5,757.2,745.2 "CockroachDB - Workload: MoVR - Concurrency: 256 (ops/s)",HIB,748.2,750.5,751.5 "CockroachDB - Workload: MoVR - Concurrency: 512 (ops/s)",HIB,745.5,750.7,744 "nginx - Connections: 500 (Reqs/sec)",HIB,157063.78,158866.84,158520.97 "Apache HTTP Server - Concurrent Requests: 500 (Reqs/sec)",HIB,132220.73,136743.33,138201.89 "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,205.6428,205.9021,205.7726 "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,310.2272,309.49,310.1225 "Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,586.7169,587.6973,587.2248 "Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,108.3637,108.2336,108.4369 "Neural Magic DeepSparse - Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,68.6185,68.5508,68.5785 "Neural Magic DeepSparse - Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,931.458,931.5601,931.1154 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,870.121,869.7454,868.9482 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,73.2014,73.2313,73.1792 "VVenC - Video Input: Bosphorus 4K - Video Preset: Faster (FPS)",HIB,8.875,9.131,9.358 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,868.7766,868.3274,871.1536 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,73.1711,72.9076,72.9975 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,207.5543,206.8781,207.6329 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,307.2889,308.4776,307.5814 "Build2 - Time To Compile (sec)",LIB,67.557,63.331,63.672 "RocksDB - Test: Update Random (Op/s)",HIB,294796,277428,292628 "RocksDB - Test: Read Random Write Random (Op/s)",HIB,1926550,1867319,1884492 "John The Ripper - Test: MD5 (Real C/S)",HIB,10348000,10330000,10376000 "RocksDB - Test: Read While Writing (Op/s)",HIB,13440214,11473082,16535579 "John The Ripper - Test: HMAC-SHA512 (Real C/S)",HIB,91862000,80447000,83472000 "OpenSSL - Algorithm: RSA4096 (verify/s)",HIB,1780535.1,1779979.3,1780224.1 "OpenSSL - Algorithm: RSA4096 (sign/s)",HIB,27007.5,27049.8,26996.1 "RocksDB - Test: Random Read (Op/s)",HIB,454636874,452696371,454644374 "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,23.6606,23.6345,24.6893 "Neural Magic DeepSparse - Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream (items/sec)",HIB,42.229,42.2754,40.4664 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,17.1168,17.2177,17.6312 "Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream (items/sec)",HIB,58.3893,58.0406,56.6843 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,104.8392,104.7265,104.9844 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,609.6225,609.857,607.0094 "Neural Magic DeepSparse - Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream (ms/batch)",LIB,9.0399,8.8949,9.3134 "Neural Magic DeepSparse - Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream (items/sec)",HIB,110.5796,112.3699,107.3193 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (ms/batch)",LIB,48.7459,47.992,48.9857 "Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream (items/sec)",HIB,20.5096,20.8324,20.409 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (ms/batch)",LIB,48.0358,48.1644,48.8033 "Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream (items/sec)",HIB,20.8125,20.7576,20.4849 "Blender - Blend File: Pabellon Barcelona - Compute: CPU-Only (sec)",LIB,45.39,46.05,45.67 "VVenC - Video Input: Bosphorus 1080p - Video Preset: Fast (FPS)",HIB,14.659,14.74,14.878 "Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,155.8199,155.8168,155.3409 "Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,409.6817,409.3953,410.158 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,76.9866,77.1093,77.3016 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,829.9415,828.026,826.5131 "Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (ms/batch)",LIB,34.5599,34.7463,34.5793 "Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream (items/sec)",HIB,28.9126,28.7579,28.8952 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (ms/batch)",LIB,6.5656,6.5727,6.6621 "Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream (items/sec)",HIB,152.2579,152.0922,150.0467 "SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 4K (FPS)",HIB,4.699,4.765,4.769 "Blender - Blend File: Classroom - Compute: CPU-Only (sec)",LIB,37.2,37.33,37.37 "Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream (ms/batch)",LIB,8.9373,8.9292,8.97 "Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream (items/sec)",HIB,111.844,111.9477,111.4342 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (ms/batch)",LIB,6.7151,6.738,6.748 "Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream (items/sec)",HIB,148.8634,148.3552,148.1303 "Opus Codec Encoding - WAV To Opus Encode (sec)",LIB,31.86,31.899,32.014 "VVenC - Video Input: Bosphorus 1080p - Video Preset: Faster (FPS)",HIB,23.518,24.049,23.082 "QuantLib - (MFLOPS)",HIB,2765.5,2758.8,2760.6 "John The Ripper - Test: WPA PSK (Real C/S)",HIB,391304,394864,394449 "John The Ripper - Test: bcrypt (Real C/S)",HIB,165909,168729,167500 "John The Ripper - Test: Blowfish (Real C/S)",HIB,158999,169154,169113 "GROMACS - Implementation: MPI CPU - Input: water_GMX50_bare (Ns/Day)",HIB,10.335,11.098,11.133 "Timed Linux Kernel Compilation - Build: defconfig (sec)",LIB,31.057,22.631,22.582 "uvg266 - Video Input: Bosphorus 4K - Video Preset: Slow (FPS)",HIB,24.73,24.79,24.7 "uvg266 - Video Input: Bosphorus 4K - Video Preset: Medium (FPS)",HIB,27.17,27.33,27.26 "SPECFEM3D - Model: Water-layered Halfspace (sec)",LIB,17.327457161,17.72543332,17.860339123 "SPECFEM3D - Model: Layered Halfspace (sec)",LIB,17.286012141,16.071385364,16.288745552 "Blender - Blend File: Fishy Cat - Compute: CPU-Only (sec)",LIB,18.53,18.74,18.72 "SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 1080p (FPS)",HIB,10.075,10.154,10.16 "Blender - Blend File: BMW27 - Compute: CPU-Only (sec)",LIB,14.88,14.86,14.62 "Timed FFmpeg Compilation - Time To Compile (sec)",LIB,15.7,13.657,13.71 "uvg266 - Video Input: Bosphorus 4K - Video Preset: Very Fast (FPS)",HIB,46.42,44.67,43.75 "uvg266 - Video Input: Bosphorus 4K - Video Preset: Super Fast (FPS)",HIB,45.43,45.07,44.29 "SPECFEM3D - Model: Homogeneous Halfspace (sec)",LIB,10.329585274,10.107559726,9.966862195 "SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 4K (FPS)",HIB,66.311,68.75,68.693 "uvg266 - Video Input: Bosphorus 4K - Video Preset: Ultra Fast (FPS)",HIB,47.56,46.27,46.24 "SPECFEM3D - Model: Tomographic Model (sec)",LIB,8.348192148,8.303506049,8.278936477 "uvg266 - Video Input: Bosphorus 1080p - Video Preset: Slow (FPS)",HIB,60.62,60.72,60.15 "SPECFEM3D - Model: Mount St. Helens (sec)",LIB,6.74456464,6.630654167,6.834107424 "Embree - Binary: Pathtracer ISPC - Model: Asian Dragon (FPS)",HIB,69.2993,82.5412,79.6439 "Embree - Binary: Pathtracer - Model: Asian Dragon (FPS)",HIB,72.6012,83.2187,85.2372 "uvg266 - Video Input: Bosphorus 1080p - Video Preset: Medium (FPS)",HIB,67.11,67.02,67.15 "SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 1080p (FPS)",HIB,103.432,109.923,105.24 "SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,146.385,174.033,180.025 "Google Draco - Model: Church Facade (ms)",LIB,5872,5856,5876 "Embree - Binary: Pathtracer ISPC - Model: Crown (FPS)",HIB,115.1609,117.8975,117.6753 "Google Draco - Model: Lion (ms)",LIB,4954,4942,4951 "Embree - Binary: Pathtracer - Model: Crown (FPS)",HIB,128.024,128.0153,129.4073 "SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 4K (FPS)",HIB,187.16,173.18,180.541 "uvg266 - Video Input: Bosphorus 1080p - Video Preset: Very Fast (FPS)",HIB,158.96,162.07,170.1 "uvg266 - Video Input: Bosphorus 1080p - Video Preset: Super Fast (FPS)",HIB,166.1,165.32,165.97 "uvg266 - Video Input: Bosphorus 1080p - Video Preset: Ultra Fast (FPS)",HIB,172.09,168.21,173.89 "SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 1080p (FPS)",HIB,484.429,521.271,571.56 "SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 1080p (FPS)",HIB,500.494,541.906,527.027 "nginx - Connections: 1000 (Reqs/sec)",HIB,,, "DeepRec - Model: BST - Data Type: BF16 (Throughput)",HIB,,, "DeepRec - Model: BST - Data Type: FP32 (Throughput)",HIB,,, "DeepRec - Model: DLRM - Data Type: BF16 (Throughput)",HIB,,, "DeepRec - Model: DIN - Data Type: FP32 (Throughput)",HIB,,, "DeepRec - Model: MMOE - Data Type: FP32 (Throughput)",HIB,,, "DeepRec - Model: DLRM - Data Type: FP32 (Throughput)",HIB,,, "DeepRec - Model: DIN - Data Type: BF16 (Throughput)",HIB,,, "DeepRec - Model: DCNv2 - Data Type: FP32 (Throughput)",HIB,,, "DeepRec - Model: DCNv2 - Data Type: BF16 (Throughput)",HIB,,, "DeepRec - Model: MMOE - Data Type: BF16 (Throughput)",HIB,,, "DeepRec - Model: PLE - Data Type: FP32 (Throughput)",HIB,,, "DeepRec - Model: PLE - Data Type: BF16 (Throughput)",HIB,,, "Apache HTTP Server - Concurrent Requests: 1000 (Reqs/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_int8_pretrained_model - Batch Size: 960 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_int8_pretrained_model - Batch Size: 512 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_int8_pretrained_model - Batch Size: 256 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_fp32_pretrained_model - Batch Size: 960 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_fp32_pretrained_model - Batch Size: 512 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_fp32_pretrained_model - Batch Size: 256 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_int8_pretrained_model - Batch Size: 960 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_int8_pretrained_model - Batch Size: 512 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_int8_pretrained_model - Batch Size: 256 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_fp32_pretrained_model - Batch Size: 960 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_fp32_pretrained_model - Batch Size: 512 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_fp32_pretrained_model - Batch Size: 256 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_int8_pretrained_model - Batch Size: 96 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_int8_pretrained_model - Batch Size: 64 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_int8_pretrained_model - Batch Size: 32 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_int8_pretrained_model - Batch Size: 16 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_fp32_pretrained_model - Batch Size: 96 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_fp32_pretrained_model - Batch Size: 64 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_fp32_pretrained_model - Batch Size: 32 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_fp32_pretrained_model - Batch Size: 16 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_int8_pretrained_model - Batch Size: 96 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_int8_pretrained_model - Batch Size: 64 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_int8_pretrained_model - Batch Size: 32 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_int8_pretrained_model - Batch Size: 16 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_fp32_pretrained_model - Batch Size: 96 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_fp32_pretrained_model - Batch Size: 64 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_fp32_pretrained_model - Batch Size: 32 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_fp32_pretrained_model - Batch Size: 16 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_int8_pretrained_model - Batch Size: 1 (images/sec)",HIB,,, "Intel TensorFlow - Model: mobilenetv1_fp32_pretrained_model - Batch Size: 1 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_int8_pretrained_model - Batch Size: 1 (images/sec)",HIB,,, "Intel TensorFlow - Model: inceptionv4_fp32_pretrained_model - Batch Size: 1 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_int8_pretrained_model - Batch Size: 960 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_int8_pretrained_model - Batch Size: 512 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_int8_pretrained_model - Batch Size: 256 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_fp32_pretrained_model - Batch Size: 960 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_fp32_pretrained_model - Batch Size: 512 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_fp32_pretrained_model - Batch Size: 256 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_int8_pretrained_model - Batch Size: 96 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_int8_pretrained_model - Batch Size: 64 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_int8_pretrained_model - Batch Size: 32 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_int8_pretrained_model - Batch Size: 16 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_fp32_pretrained_model - Batch Size: 96 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_fp32_pretrained_model - Batch Size: 64 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_fp32_pretrained_model - Batch Size: 32 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_fp32_pretrained_model - Batch Size: 16 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_int8_pretrained_model - Batch Size: 1 (images/sec)",HIB,,, "Intel TensorFlow - Model: resnet50_fp32_pretrained_model - Batch Size: 1 (images/sec)",HIB,,, "Apache HTTP Server - Concurrent Requests: 200 (Reqs/sec)",HIB,,, "Apache HTTP Server - Concurrent Requests: 100 (Reqs/sec)",HIB,,, "nginx - Connections: 200 (Reqs/sec)",HIB,,, "nginx - Connections: 100 (Reqs/sec)",HIB,,,