2024 year

AMD Ryzen Threadripper PRO 5965WX 24-Cores testing with a ASUS Pro WS WRX80E-SAGE SE WIFI (1201 BIOS) and ASUS NVIDIA NV106 2GB on Ubuntu 23.10 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 2402040-NE-2024YEAR116
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
BLAS (Basic Linear Algebra Sub-Routine) Tests 2 Tests
CPU Massive 4 Tests
Creator Workloads 2 Tests
Encoding 2 Tests
HPC - High Performance Computing 6 Tests
Large Language Models 2 Tests
Machine Learning 6 Tests
Multi-Core 2 Tests
Python Tests 3 Tests
Video Encoding 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
February 03
  1 Hour, 38 Minutes
b
February 04
  4 Hours, 50 Minutes
c
February 04
  1 Hour, 37 Minutes
d
February 04
  1 Hour, 34 Minutes
Invert Hiding All Results Option
  2 Hours, 25 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):

2024 year, "PyTorch 2.1 - Device: CPU - Batch Size: 1 - Model: ResNet-50", Higher Results Are Better "a",40.679842279448 "b",40.082710437007,40.454003410792,40.730354071499 "c",40.817990546687 "d",40.346476971594 "PyTorch 2.1 - Device: CPU - Batch Size: 16 - Model: ResNet-50", Higher Results Are Better "a",32.504968667824 "b",32.226463723445,32.218682799793,31.849792803154 "c",31.64661820166 "d",32.208723525546 "PyTorch 2.1 - Device: CPU - Batch Size: 256 - Model: ResNet-50", Higher Results Are Better "a",31.922676597644 "b",32.180518448823,31.948194331913,32.315159242898 "c",31.585857257287 "d",32.073809504371 "Quicksilver 20230818 - Input: CTS2", Higher Results Are Better "a", "b",20640000,20640000,20660000 "c", "d", "Quicksilver 20230818 - Input: CORAL2 P1", Higher Results Are Better "a", "b",24250000,24230000,24210000 "c", "d", "Quicksilver 20230818 - Input: CORAL2 P2", Higher Results Are Better "a", "b",24030000,24030000,24020000 "c", "d", "rav1e 0.7 - Speed: 1", Higher Results Are Better "a", "b",1.041,1.05,1.053 "c", "d", "rav1e 0.7 - Speed: 5", Higher Results Are Better "a", "b",3.814,3.792,3.767 "c", "d", "rav1e 0.7 - Speed: 6", Higher Results Are Better "a", "b",5.302,5.298,5.276 "c", "d", "rav1e 0.7 - Speed: 10", Higher Results Are Better "a", "b",10.477,10.932,11.153,10.975,10.889 "c", "d", "SVT-AV1 1.8 - Encoder Mode: Preset 4 - Input: Bosphorus 4K", Higher Results Are Better "a", "b",6.652,6.656,6.699 "c", "d", "SVT-AV1 1.8 - Encoder Mode: Preset 8 - Input: Bosphorus 4K", Higher Results Are Better "a", "b",61.772,61.965,61.753 "c", "d", "SVT-AV1 1.8 - Encoder Mode: Preset 12 - Input: Bosphorus 4K", Higher Results Are Better "a", "b",192.47,188.809,189.928 "c", "d", "SVT-AV1 1.8 - Encoder Mode: Preset 13 - Input: Bosphorus 4K", Higher Results Are Better "a", "b",192.047,191.805,194.326 "c", "d", "SVT-AV1 1.8 - Encoder Mode: Preset 4 - Input: Bosphorus 1080p", Higher Results Are Better "a", "b",18.598,18.843,18.604 "c", "d", "SVT-AV1 1.8 - Encoder Mode: Preset 8 - Input: Bosphorus 1080p", Higher Results Are Better "a", "b",124.476,122.731,122.673 "c", "d", "SVT-AV1 1.8 - Encoder Mode: Preset 12 - Input: Bosphorus 1080p", Higher Results Are Better "a", "b",515.356,486.262,505.208,512.629,513.525 "c", "d", "SVT-AV1 1.8 - Encoder Mode: Preset 13 - Input: Bosphorus 1080p", Higher Results Are Better "a", "b",568.143,587.126,563.856 "c", "d", "TensorFlow 2.12 - Device: CPU - Batch Size: 1 - Model: VGG-16", Higher Results Are Better "a", "b",2.69,2.7,2.71 "c", "d", "TensorFlow 2.12 - Device: CPU - Batch Size: 1 - Model: AlexNet", Higher Results Are Better "a", "b",6.21,6.22,6.25 "c", "d", "TensorFlow 2.12 - Device: CPU - Batch Size: 16 - Model: VGG-16", Higher Results Are Better "a", "b",8.4,8.49,8.48 "c", "d", "TensorFlow 2.12 - Device: CPU - Batch Size: 16 - Model: AlexNet", Higher Results Are Better "a", "b",100.39,99.93,99.7 "c", "d", "TensorFlow 2.12 - Device: CPU - Batch Size: 1 - Model: GoogLeNet", Higher Results Are Better "a", "b",9.9,9.73,9.59 "c", "d", "TensorFlow 2.12 - Device: CPU - Batch Size: 1 - Model: ResNet-50", Higher Results Are Better "a", "b",8.8,8.87,8.69 "c", "d", "TensorFlow 2.12 - Device: CPU - Batch Size: 16 - Model: GoogLeNet", Higher Results Are Better "a", "b",60.64,60.43,59.48 "c", "d", "TensorFlow 2.12 - Device: CPU - Batch Size: 16 - Model: ResNet-50", Higher Results Are Better "a", "b",19.3,19.45,19.59 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",26.7262,26.6727,26.5446 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",18.3439,18.3345,18.3166 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",682.6459,680.3445,680.0209 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",191.8182,193.7694,193.7443 "c", "d", "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",304.659,304.6272,305.0275 "c", "d", "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",155.0257,155.4929,155.9324 "c", "d", "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",1973.8748,1972.4988,1941.7404 "c", "d", "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",751.0971,755.4015,751.8365 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",148.92,147.6965,148.1 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",98.5045,98.4539,98.732 "c", "d", "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",32.315,32.313,32.4583 "c", "d", "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",17.1551,17.0919,17.1542 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",306.8158,304.2259,305.0967 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",155.5636,155.6699,155.3871 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",149.7947,149.752,149.7987 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",99.2185,98.2307,98.7876 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",221.6572,221.9297,221.5289 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",111.1165,111.8055,110.9456 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",30.2387,30.3217,30.2823 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",21.3779,21.4829,21.5621 "c", "d", "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",334.2437,332.9219,332.9365 "c", "d", "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",75.6765,75.609,75.2347 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",26.6454,26.7189,26.6374 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",18.3794,18.4193,18.4012 "c", "d", "CacheBench - Test: Read", Higher Results Are Better "a", "b",11543.328175,11543.026626,11543.139261 "c", "d", "CacheBench - Test: Write", Higher Results Are Better "a", "b",69137.936779,69136.600095,69147.056102 "c", "d", "CacheBench - Test: Read / Modify / Write", Higher Results Are Better "a", "b",129690.835604,130843.381856,129675.327553 "c", "d", "LZ4 Compression 1.9.4 - Compression Level: 1 - Compression Speed", Higher Results Are Better "a", "b",829.9,828.11,830.07 "c", "d", "LZ4 Compression 1.9.4 - Compression Level: 1 - Decompression Speed", Higher Results Are Better "a", "b",5018.6,5022.8,5018.5 "c", "d", "LZ4 Compression 1.9.4 - Compression Level: 3 - Compression Speed", Higher Results Are Better "a", "b",130.85,131.7,130.75 "c", "d", "LZ4 Compression 1.9.4 - Compression Level: 3 - Decompression Speed", Higher Results Are Better "a", "b",4596.7,4598.8,4598.3 "c", "d", "LZ4 Compression 1.9.4 - Compression Level: 9 - Compression Speed", Higher Results Are Better "a", "b",44.52,44.44,44.47 "c", "d", "LZ4 Compression 1.9.4 - Compression Level: 9 - Decompression Speed", Higher Results Are Better "a", "b",4839.2,4842.1,4842.9 "c", "d", "LeelaChessZero 0.30 - Backend: BLAS", Higher Results Are Better "a", "b",219,218,219 "c", "d", "LeelaChessZero 0.30 - Backend: Eigen", Higher Results Are Better "a", "b",145,143,150 "c", "d", "Speedb 2.7 - Test: Random Fill", Higher Results Are Better "a", "b",553578,548488,562926 "c", "d", "Speedb 2.7 - Test: Random Read", Higher Results Are Better "a", "b",147569457,147439695,147287489 "c", "d", "Speedb 2.7 - Test: Update Random", Higher Results Are Better "a", "b",421338,410909,424298 "c", "d", "Speedb 2.7 - Test: Sequential Fill", Higher Results Are Better "a", "b",623446,620332,612551 "c", "d", "Speedb 2.7 - Test: Random Fill Sync", Higher Results Are Better "a", "b",47690,47604,47831 "c", "d", "Speedb 2.7 - Test: Read While Writing", Higher Results Are Better "a", "b",7039337,6983972,7187912 "c", "d", "Speedb 2.7 - Test: Read Random Write Random", Higher Results Are Better "a", "b",2309421,2305238,2308398 "c", "d", "Llama.cpp b1808 - Model: llama-2-7b.Q4_0.gguf", Higher Results Are Better "a", "b",20.71,20.69,21.67,20.73 "c", "d", "Llama.cpp b1808 - Model: llama-2-13b.Q4_0.gguf", Higher Results Are Better "a", "b",11.25,11.27,11.44 "c", "d", "Llama.cpp b1808 - Model: llama-2-70b-chat.Q5_0.gguf", Higher Results Are Better "a", "b",1.94,1.95,1.94 "c", "d", "Llamafile 0.6 - Test: llava-v1.5-7b-q4 - Acceleration: CPU", Higher Results Are Better "a", "b",17.26,17.28,17.25 "c", "d", "Llamafile 0.6 - Test: mistral-7b-instruct-v0.2.Q8_0 - Acceleration: CPU", Higher Results Are Better "a", "b",10.15,10.13,10.16 "c", "d", "Llamafile 0.6 - Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU", Higher Results Are Better "a", "b",3.25,3.25,3.25 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",448.3898,449.3251,449.0088 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",54.5002,54.5278,54.5814 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",17.5576,17.6171,17.6249 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",5.21,5.1576,5.1584 "c", "d", "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",39.3408,39.3499,39.3111 "c", "d", "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",6.4418,6.4223,6.405 "c", "d", "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",6.0658,6.0703,6.1668 "c", "d", "Neural Magic DeepSparse 1.6 - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",1.328,1.3205,1.327 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",80.4806,81.1569,80.902 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",10.1429,10.1471,10.1185 "c", "d", "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",369.8642,370.1832,369.2686 "c", "d", "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",58.2767,58.4916,58.2786 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",39.0795,39.4009,39.2862 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",6.4198,6.415,6.4277 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",80.0011,80.0804,80.0594 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",10.0731,10.1738,10.1169 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",54.0553,54.0151,54.1133 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",8.9897,8.9339,9.0029 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",394.3486,394.3844,395.5947 "c", "d", "Neural Magic DeepSparse 1.6 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",46.7549,46.5255,46.3554 "c", "d", "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",35.8823,36.0154,36.0202 "c", "d", "Neural Magic DeepSparse 1.6 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",13.2093,13.2207,13.2865 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",447.5306,448.6227,447.9691 "c", "d", "Neural Magic DeepSparse 1.6 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",54.3955,54.276,54.3305 "c", "d", "Y-Cruncher 0.8.3 - Pi Digits To Calculate: 1B", Lower Results Are Better "a", "b",15.474,15.506,15.511 "c", "d", "Y-Cruncher 0.8.3 - Pi Digits To Calculate: 500M", Lower Results Are Better "a", "b",7.354,7.335,7.358 "c", "d",