xeon jan
Intel Xeon Silver 4216 testing with a TYAN S7100AG2NR (V4.02 BIOS) and ASPEED on Debian 12 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2401144-NE-XEONJAN1706&grs&sro.
Speedb
Test: Random Fill Sync
Speedb
Test: Random Fill
Speedb
Test: Update Random
TensorFlow
Device: CPU - Batch Size: 1 - Model: GoogLeNet
Llama.cpp
Model: llama-2-7b.Q4_0.gguf
SVT-AV1
Encoder Mode: Preset 12 - Input: Bosphorus 4K
Speedb
Test: Read While Writing
SVT-AV1
Encoder Mode: Preset 12 - Input: Bosphorus 1080p
Neural Magic DeepSparse
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
LeelaChessZero
Backend: Eigen
CacheBench
Test: Read / Modify / Write
Speedb
Test: Sequential Fill
LeelaChessZero
Backend: BLAS
PyTorch
Device: CPU - Batch Size: 1 - Model: ResNet-50
SVT-AV1
Encoder Mode: Preset 13 - Input: Bosphorus 1080p
SVT-AV1
Encoder Mode: Preset 8 - Input: Bosphorus 1080p
PyTorch
Device: CPU - Batch Size: 16 - Model: ResNet-50
Quicksilver
Input: CTS2
SVT-AV1
Encoder Mode: Preset 4 - Input: Bosphorus 1080p
SVT-AV1
Encoder Mode: Preset 4 - Input: Bosphorus 4K
SVT-AV1
Encoder Mode: Preset 8 - Input: Bosphorus 4K
Speedb
Test: Random Read
TensorFlow
Device: CPU - Batch Size: 1 - Model: ResNet-50
Y-Cruncher
Pi Digits To Calculate: 1B
Neural Magic DeepSparse
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream
PyTorch
Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l
Llama.cpp
Model: llama-2-13b.Q4_0.gguf
PyTorch
Device: CPU - Batch Size: 32 - Model: ResNet-152
Neural Magic DeepSparse
Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream
PyTorch
Device: CPU - Batch Size: 16 - Model: ResNet-152
SVT-AV1
Encoder Mode: Preset 13 - Input: Bosphorus 4K
Speedb
Test: Read Random Write Random
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream
TensorFlow
Device: CPU - Batch Size: 1 - Model: VGG-16
PyTorch
Device: CPU - Batch Size: 1 - Model: ResNet-152
Neural Magic DeepSparse
Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream
PyTorch
Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l
PyTorch
Device: CPU - Batch Size: 32 - Model: ResNet-50
TensorFlow
Device: CPU - Batch Size: 1 - Model: AlexNet
Neural Magic DeepSparse
Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream
PyTorch
Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l
Quicksilver
Input: CORAL2 P2
Llama.cpp
Model: llama-2-70b-chat.Q5_0.gguf
Neural Magic DeepSparse
Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream
TensorFlow
Device: CPU - Batch Size: 16 - Model: AlexNet
Quicksilver
Input: CORAL2 P1
Neural Magic DeepSparse
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
TensorFlow
Device: CPU - Batch Size: 16 - Model: GoogLeNet
Neural Magic DeepSparse
Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream
Y-Cruncher
Pi Digits To Calculate: 500M
Neural Magic DeepSparse
Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream
TensorFlow
Device: CPU - Batch Size: 16 - Model: ResNet-50
Neural Magic DeepSparse
Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream
Neural Magic DeepSparse
Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream
CacheBench
Test: Write
Neural Magic DeepSparse
Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream
CacheBench
Test: Read
TensorFlow
Device: CPU - Batch Size: 16 - Model: VGG-16
Phoronix Test Suite v10.8.5