Intel Xeon Silver 4216 testing with a TYAN S7100AG2NR (V4.02 BIOS) and ASPEED on Debian 12 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 2401144-NE-XEONJAN1706
xeon jan
Intel Xeon Silver 4216 testing with a TYAN S7100AG2NR (V4.02 BIOS) and ASPEED on Debian 12 via the Phoronix Test Suite.
,,"a","b","c"
Processor,,Intel Xeon Silver 4216 @ 3.20GHz (16 Cores / 32 Threads),Intel Xeon Silver 4216 @ 3.20GHz (16 Cores / 32 Threads),Intel Xeon Silver 4216 @ 3.20GHz (16 Cores / 32 Threads)
Motherboard,,TYAN S7100AG2NR (V4.02 BIOS),TYAN S7100AG2NR (V4.02 BIOS),TYAN S7100AG2NR (V4.02 BIOS)
Chipset,,Intel Sky Lake-E DMI3 Registers,Intel Sky Lake-E DMI3 Registers,Intel Sky Lake-E DMI3 Registers
Memory,,6 x 8 GB DDR4-2400MT/s,6 x 8 GB DDR4-2400MT/s,6 x 8 GB DDR4-2400MT/s
Disk,,240GB Corsair Force MP500,240GB Corsair Force MP500,240GB Corsair Force MP500
Graphics,,ASPEED,ASPEED,ASPEED
Audio,,Realtek ALC892,Realtek ALC892,Realtek ALC892
Network,,2 x Intel I350,2 x Intel I350,2 x Intel I350
OS,,Debian 12,Debian 12,Debian 12
Kernel,,6.1.0-11-amd64 (x86_64),6.1.0-11-amd64 (x86_64),6.1.0-11-amd64 (x86_64)
Display Server,,X Server,X Server,X Server
Compiler,,GCC 12.2.0,GCC 12.2.0,GCC 12.2.0
File-System,,ext4,ext4,ext4
Screen Resolution,,1024x768,1024x768,1024x768
,,"a","b","c"
"Speedb - Test: Random Fill Sync (Op/s)",HIB,8962,13397,10150
"Speedb - Test: Random Fill (Op/s)",HIB,379730,298026,377206
"Speedb - Test: Update Random (Op/s)",HIB,172891,163726,151137
"TensorFlow - Device: CPU - Batch Size: 1 - Model: GoogLeNet (images/sec)",HIB,17.26,15.86,16.19
"Llama.cpp - Model: llama-2-7b.Q4_0.gguf (Tokens/sec)",HIB,16.95,15.89,16.55
"SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 4K (FPS)",HIB,82.805,78.544,82.222
"Speedb - Test: Read While Writing (Op/s)",HIB,3897119,3867484,4014397
"SVT-AV1 - Encoder Mode: Preset 12 - Input: Bosphorus 1080p (FPS)",HIB,165.265,170.98,168.012
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,7.5161,7.2935,7.5416
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,7.3201,7.5195,7.2847
"LeelaChessZero - Backend: Eigen (Nodes/s)",HIB,33,33,32
"CacheBench - Test: Read / Modify / Write (MB/s)",HIB,61680.563289,59877.337189,60843.704817
"Speedb - Test: Sequential Fill (Op/s)",HIB,565169,558662,549382
"LeelaChessZero - Backend: BLAS (Nodes/s)",HIB,37,38,37
"PyTorch - Device: CPU - Batch Size: 1 - Model: ResNet-50 (batches/sec)",HIB,29.51,29.64,28.89
"SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 1080p (FPS)",HIB,188.993,184.724,187.023
"SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 1080p (FPS)",HIB,45.633,46.686,45.935
"PyTorch - Device: CPU - Batch Size: 16 - Model: ResNet-50 (batches/sec)",HIB,21.57,21.27,21.73
"Quicksilver - Input: CTS2 (Figure Of Merit)",HIB,8446000,8497000,8607000
"SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 1080p (FPS)",HIB,7.326,7.379,7.251
"SVT-AV1 - Encoder Mode: Preset 4 - Input: Bosphorus 4K (FPS)",HIB,2.462,2.423,2.421
"SVT-AV1 - Encoder Mode: Preset 8 - Input: Bosphorus 4K (FPS)",HIB,24.384,23.99,24.069
"Speedb - Test: Random Read (Op/s)",HIB,53271554,52915603,52443533
"TensorFlow - Device: CPU - Batch Size: 1 - Model: ResNet-50 (images/sec)",HIB,4.81,4.87,4.88
"Y-Cruncher - Pi Digits To Calculate: 1B (sec)",LIB,46.091,45.445,45.928
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,14.384,14.5017,14.3009
"PyTorch - Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l (batches/sec)",HIB,4.72,4.76,4.70
"Llama.cpp - Model: llama-2-13b.Q4_0.gguf (Tokens/sec)",HIB,8.7,8.73,8.62
"PyTorch - Device: CPU - Batch Size: 32 - Model: ResNet-152 (batches/sec)",HIB,8.18,8.09,8.08
"Neural Magic DeepSparse - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,1061.8943,1073.1318,1060.5969
"PyTorch - Device: CPU - Batch Size: 16 - Model: ResNet-152 (batches/sec)",HIB,8.14,8.13,8.22
"SVT-AV1 - Encoder Mode: Preset 13 - Input: Bosphorus 4K (FPS)",HIB,82.392,82.623,83.269
"Speedb - Test: Read Random Write Random (Op/s)",HIB,1640953,1658156,1656172
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,28.1401,27.8492,27.95
"Neural Magic DeepSparse - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,283.9607,286.9078,285.941
"TensorFlow - Device: CPU - Batch Size: 1 - Model: VGG-16 (images/sec)",HIB,3.27,3.24,3.26
"PyTorch - Device: CPU - Batch Size: 1 - Model: ResNet-152 (batches/sec)",HIB,11.11,11.17,11.07
"Neural Magic DeepSparse - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,1071.4101,1063.8379,1072.9766
"PyTorch - Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l (batches/sec)",HIB,4.79,4.75,4.75
"PyTorch - Device: CPU - Batch Size: 32 - Model: ResNet-50 (batches/sec)",HIB,21.56,21.64,21.74
"TensorFlow - Device: CPU - Batch Size: 1 - Model: AlexNet (images/sec)",HIB,18.21,18.25,18.35
"Neural Magic DeepSparse - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,552.534,549.3992,553.4687
"PyTorch - Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l (batches/sec)",HIB,6.91,6.90,6.95
"Quicksilver - Input: CORAL2 P2 (Figure Of Merit)",HIB,9287000,9354000,9308000
"Llama.cpp - Model: llama-2-70b-chat.Q5_0.gguf (Tokens/sec)",HIB,1.5,1.51,1.5
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,732.3634,736.8677,734.4208
"Neural Magic DeepSparse - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,10.9015,10.8351,10.8705
"TensorFlow - Device: CPU - Batch Size: 16 - Model: AlexNet (images/sec)",HIB,83.17,82.83,83.33
"Quicksilver - Input: CORAL2 P1 (Figure Of Merit)",HIB,10170000,10110000,10150000
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,64.9099,64.5367,64.617
"TensorFlow - Device: CPU - Batch Size: 16 - Model: GoogLeNet (images/sec)",HIB,47.63,47.51,47.36
"Neural Magic DeepSparse - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,123.2229,123.8886,123.7819
"Y-Cruncher - Pi Digits To Calculate: 500M (sec)",LIB,20.623,20.682,20.575
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,9.4169,9.4557,9.4646
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,116.1827,115.8799,116.403
"Neural Magic DeepSparse - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,68.7595,68.9544,68.677
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,164.6289,164.5919,164.0809
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,125.9588,126.098,125.7734
"TensorFlow - Device: CPU - Batch Size: 16 - Model: ResNet-50 (images/sec)",HIB,16.22,16.25,16.21
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,63.4829,63.3871,63.5329
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,116.2812,116.0381,116.0803
"Neural Magic DeepSparse - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,68.7723,68.9149,68.8893
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,165.9672,165.6879,165.8752
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,48.1923,48.2735,48.2187
"Neural Magic DeepSparse - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream (items/sec)",HIB,48.5709,48.598,48.652
"CacheBench - Test: Write (MB/s)",HIB,23161.605712,23134.972437,23165.587056
"Neural Magic DeepSparse - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream (ms/batch)",LIB,845.9518,845.9952,845.2007
"CacheBench - Test: Read (MB/s)",HIB,6062.370107,6058.744667,6057.993007
"TensorFlow - Device: CPU - Batch Size: 16 - Model: VGG-16 (images/sec)",HIB,5.96,5.96,5.96