xeon jan

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
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:

BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
CPU Massive 4 Tests
HPC - High Performance Computing 5 Tests
Machine Learning 5 Tests
Python Tests 3 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
a
January 14
  1 Hour, 57 Minutes
b
January 14
  1 Hour, 56 Minutes
c
January 15
  1 Hour, 57 Minutes
Invert Hiding All Results Option
  1 Hour, 57 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):

xeon jan Suite 1.0.0 System Test suite extracted from xeon jan. pts/speedb-1.0.1 --benchmarks="fillsync" Test: Random Fill Sync pts/speedb-1.0.1 --benchmarks="fillrandom" Test: Random Fill pts/speedb-1.0.1 --benchmarks="updaterandom" Test: Update Random pts/tensorflow-2.1.1 --device cpu --batch_size=1 --model=googlenet Device: CPU - Batch Size: 1 - Model: GoogLeNet pts/llama-cpp-1.0.0 -m ../llama-2-7b.Q4_0.gguf Model: llama-2-7b.Q4_0.gguf pts/svt-av1-2.11.1 --preset 12 -i Bosphorus_3840x2160.y4m -w 3840 -h 2160 Encoder Mode: Preset 12 - Input: Bosphorus 4K pts/speedb-1.0.1 --benchmarks="readwhilewriting" Test: Read While Writing pts/svt-av1-2.11.1 --preset 12 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Preset 12 - Input: Bosphorus 1080p pts/deepsparse-1.6.0 zoo:nlp/document_classification/obert-base/pytorch/huggingface/imdb/base-none --scenario async Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream pts/deepsparse-1.6.0 zoo:nlp/token_classification/bert-base/pytorch/huggingface/conll2003/base-none --scenario async Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream pts/lczero-1.7.0 -b eigen Backend: Eigen pts/cachebench-1.2.0 -b Test: Read / Modify / Write pts/speedb-1.0.1 --benchmarks="fillseq" Test: Sequential Fill pts/lczero-1.7.0 -b blas Backend: BLAS pts/pytorch-1.0.1 cpu 1 resnet50 Device: CPU - Batch Size: 1 - Model: ResNet-50 pts/svt-av1-2.11.1 --preset 13 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Preset 13 - Input: Bosphorus 1080p pts/svt-av1-2.11.1 --preset 8 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Preset 8 - Input: Bosphorus 1080p pts/pytorch-1.0.1 cpu 16 resnet50 Device: CPU - Batch Size: 16 - Model: ResNet-50 pts/quicksilver-1.0.0 ../Examples/CTS2_Benchmark/CTS2.inp Input: CTS2 pts/svt-av1-2.11.1 --preset 4 -n 160 -i Bosphorus_1920x1080_120fps_420_8bit_YUV.yuv -w 1920 -h 1080 Encoder Mode: Preset 4 - Input: Bosphorus 1080p pts/svt-av1-2.11.1 --preset 4 -n 160 -i Bosphorus_3840x2160.y4m -w 3840 -h 2160 Encoder Mode: Preset 4 - Input: Bosphorus 4K pts/svt-av1-2.11.1 --preset 8 -i Bosphorus_3840x2160.y4m -w 3840 -h 2160 Encoder Mode: Preset 8 - Input: Bosphorus 4K pts/speedb-1.0.1 --benchmarks="readrandom" Test: Random Read pts/tensorflow-2.1.1 --device cpu --batch_size=1 --model=resnet50 Device: CPU - Batch Size: 1 - Model: ResNet-50 pts/y-cruncher-1.4.0 1b Pi Digits To Calculate: 1B pts/deepsparse-1.6.0 zoo:cv/segmentation/yolact-darknet53/pytorch/dbolya/coco/pruned90-none --scenario async Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream pts/pytorch-1.0.1 cpu 16 efficientnet_v2_l Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l pts/llama-cpp-1.0.0 -m ../llama-2-13b.Q4_0.gguf Model: llama-2-13b.Q4_0.gguf pts/pytorch-1.0.1 cpu 32 resnet152 Device: CPU - Batch Size: 32 - Model: ResNet-152 pts/pytorch-1.0.1 cpu 16 resnet152 Device: CPU - Batch Size: 16 - Model: ResNet-152 pts/svt-av1-2.11.1 --preset 13 -i Bosphorus_3840x2160.y4m -w 3840 -h 2160 Encoder Mode: Preset 13 - Input: Bosphorus 4K pts/speedb-1.0.1 --benchmarks="readrandomwriterandom" Test: Read Random Write Random pts/deepsparse-1.6.0 zoo:nlp/sentiment_analysis/oberta-base/pytorch/huggingface/sst2/pruned90_quant-none --input_shapes='[1,128]' --scenario async Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream pts/tensorflow-2.1.1 --device cpu --batch_size=1 --model=vgg16 Device: CPU - Batch Size: 1 - Model: VGG-16 pts/pytorch-1.0.1 cpu 1 resnet152 Device: CPU - Batch Size: 1 - Model: ResNet-152 pts/pytorch-1.0.1 cpu 32 efficientnet_v2_l Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l pts/pytorch-1.0.1 cpu 32 resnet50 Device: CPU - Batch Size: 32 - Model: ResNet-50 pts/tensorflow-2.1.1 --device cpu --batch_size=1 --model=alexnet Device: CPU - Batch Size: 1 - Model: AlexNet pts/pytorch-1.0.1 cpu 1 efficientnet_v2_l Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l pts/quicksilver-1.0.0 ../Examples/CORAL2_Benchmark/Problem2/Coral2_P2.inp Input: CORAL2 P2 pts/llama-cpp-1.0.0 -m ../llama-2-70b-chat.Q5_0.gguf Model: llama-2-70b-chat.Q5_0.gguf pts/deepsparse-1.6.0 zoo:cv/classification/resnet_v1-50/pytorch/sparseml/imagenet/pruned95_uniform_quant-none --scenario async Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream pts/tensorflow-2.1.1 --device cpu --batch_size=16 --model=alexnet Device: CPU - Batch Size: 16 - Model: AlexNet pts/quicksilver-1.0.0 ../Examples/CORAL2_Benchmark/Problem1/Coral2_P1.inp Input: CORAL2 P1 pts/deepsparse-1.6.0 zoo:nlp/text_classification/distilbert-none/pytorch/huggingface/mnli/base-none --scenario async Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream pts/tensorflow-2.1.1 --device cpu --batch_size=16 --model=googlenet Device: CPU - Batch Size: 16 - Model: GoogLeNet pts/y-cruncher-1.4.0 500m Pi Digits To Calculate: 500M pts/deepsparse-1.6.0 zoo:nlp/question_answering/obert-large/pytorch/huggingface/squad/base-none --input_shapes='[1,128]' --scenario async Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream pts/deepsparse-1.6.0 zoo:cv/classification/resnet_v1-50/pytorch/sparseml/imagenet/base-none --scenario async Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream pts/deepsparse-1.6.0 zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/pruned85-none --scenario async Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream pts/deepsparse-1.6.0 zoo:nlp/question_answering/obert-large/pytorch/huggingface/squad/pruned97_quant-none --input_shapes='[1,128]' --scenario async Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream pts/tensorflow-2.1.1 --device cpu --batch_size=16 --model=resnet50 Device: CPU - Batch Size: 16 - Model: ResNet-50 pts/deepsparse-1.6.0 zoo:cv/classification/resnet_v1-50/pytorch/sparseml/imagenet/base-none --scenario async Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream pts/deepsparse-1.6.0 zoo:cv/detection/yolov5-s/pytorch/ultralytics/coco/base-none --scenario async Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream pts/cachebench-1.2.0 -w Test: Write pts/cachebench-1.2.0 -r Test: Read pts/tensorflow-2.1.1 --device cpu --batch_size=16 --model=vgg16 Device: CPU - Batch Size: 16 - Model: VGG-16