ddfg

2 x AMD EPYC 9684X 96-Core testing with a AMD Titanite_4G (RTI1007B BIOS) and ASPEED 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 2403164-NE-DDFG2505160
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:

CPU Massive 2 Tests
Multi-Core 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
Performance Per
Dollar
Date
Run
  Test
  Duration
a
March 16
  36 Minutes
b
March 16
  1 Hour, 48 Minutes
c
March 16
  2 Hours, 38 Minutes
d
March 16
  36 Minutes
Invert Hiding All Results Option
  1 Hour, 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):

ddfg, "Neural Magic DeepSparse 1.7 - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",24945.9471,24377.2825,25341.2394 "c",38563.2216,24331.6741,24464.3812,24483.5311,24576.1062,26400.2355,24730.7181,37947.9478,24220.0956,24398.0901,38138.0374,35373.405 "d", "Neural Magic DeepSparse 1.7 - Model: Llama2 Chat 7b Quantized - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",2.8415,2.9274,2.8133 "c",1.7148,2.9304,2.9083,2.8815,2.8685,2.6846,2.8826,1.7087,2.9431,2.9213,1.6972,1.8687 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",5.1922,5.1943,5.2463 "c",5.1667,5.2059,5.223 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",192.4648,192.3807,190.4688 "c",193.4091,191.9606,191.3307 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",17.2637,17.3266,17.3227 "c",17.2897,17.3048,17.3618 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, BERT base uncased SST2, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",5551.6684,5533.0286,5532.2449 "c",5543.0636,5539.594,5520.1235 "d", "Neural Magic DeepSparse 1.7 - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",47.8847,47.8163,48.4002 "c",47.8225,48.6184,48.2123 "d", "Neural Magic DeepSparse 1.7 - Model: Llama2 Chat 7b Quantized - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",20.8694,20.8992,20.647 "c",20.8967,20.5538,20.7273 "d", "Neural Magic DeepSparse 1.7 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",37.0129,36.8631,36.9213 "c",36.9195,36.8904,36.9549 "d", "Neural Magic DeepSparse 1.7 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",2589.789,2599.8635,2595.8765 "c",2595.333,2598.0555,2593.0478 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",715.6143,717.7053,719.1505 "c",709.0739,718.9605,719.5967 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",133.3595,132.9565,132.6291 "c",133.3179,132.5407,132.7789 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",714.2366,718.3613,719.1716 "c",702.5114,705.4365,719.8284 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",133.336,132.4933,132.5611 "c",134.8358,134.1725,132.4101 "d", "Neural Magic DeepSparse 1.7 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",14.5531,14.6388,14.6484 "c",14.6138,14.5755,14.5481 "d", "Neural Magic DeepSparse 1.7 - Model: BERT-Large, NLP Question Answering, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",68.68,68.2774,68.2341 "c",68.3947,68.5719,68.7028 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",20.6999,20.6506,20.6676 "c",20.5734,20.6334,20.6044 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",48.2915,48.4077,48.3673 "c",48.5891,48.4483,48.5159 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",20.653,20.637,20.6424 "c",20.6152,20.7336,20.6333 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",48.4021,48.4398,48.4264 "c",48.4907,48.2135,48.4482 "d", "Neural Magic DeepSparse 1.7 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",380.8443,382.4598,383.067 "c",380.8901,382.5717,383.0608 "d", "Neural Magic DeepSparse 1.7 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",250.2157,249.3491,248.6405 "c",249.6122,248.8706,248.8 "d", "Neural Magic DeepSparse 1.7 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",15.3988,15.4484,15.3474 "c",15.4314,15.3163,15.4055 "d", "Neural Magic DeepSparse 1.7 - Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",64.8629,64.6453,65.0676 "c",64.7257,65.2074,64.8336 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",4.4248,4.4265,4.4473 "c",4.4364,4.4329,4.4294 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",225.8552,225.772,224.7216 "c",225.2668,225.4448,225.6128 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",83.5472,83.87,84.1274 "c",83.6283,83.9394,84.2101 "d", "Neural Magic DeepSparse 1.7 - Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",1147.0651,1142.6569,1139.2613 "c",1145.3328,1141.428,1136.9644 "d", "Neural Magic DeepSparse 1.7 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",119.9627,120.3966,120.1767 "c",119.9131,120.6147,120.6651 "d", "Neural Magic DeepSparse 1.7 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",798.0281,795.2721,796.4897 "c",798.4029,793.5627,793.1174 "d", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",54.3538,54.4615,54.6455 "c",54.3126,54.4575,54.6063 "d", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Baseline - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",1763.0751,1759.1659,1754.1761 "c",1764.6064,1760.246,1755.0162 "d", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",5.5086,5.5157,5.5266 "c",5.5015,5.538,5.5278 "d", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Sparse INT8 - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",17378.9844,17352.9115,17319.496 "c",17399.1212,17285.0713,17315.8579 "d", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",4.7564,4.7521,4.784 "c",4.8036,4.7784,4.7805 "d", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Baseline - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",210.111,210.2997,208.9027 "c",208.0416,209.1306,209.0496 "d", "Neural Magic DeepSparse 1.7 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Lower Results Are Better "a", "b",54.3429,54.6493,54.7058 "c",54.5101,54.5031,54.6698 "d", "Neural Magic DeepSparse 1.7 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream", Higher Results Are Better "a", "b",1762.6368,1753.8814,1752.0044 "c",1758.5173,1758.5438,1752.6201 "d", "Neural Magic DeepSparse 1.7 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",4.6925,4.7162,4.7017 "c",4.6974,4.7019,4.7013 "d", "Neural Magic DeepSparse 1.7 - Model: CV Detection, YOLOv5s COCO, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",212.9901,211.9211,212.5722 "c",212.7693,212.5617,212.586 "d", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",1.2467,1.2382,1.2378 "c",1.2372,1.2395,1.2375 "d", "Neural Magic DeepSparse 1.7 - Model: ResNet-50, Sparse INT8 - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",800.719,806.1334,806.3551 "c",806.7872,805.3167,806.5975 "d", "Neural Magic DeepSparse 1.7 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream", Lower Results Are Better "a", "b",4.8131,4.7638,4.7878 "c",4.733,4.8088,4.8296 "d", "Neural Magic DeepSparse 1.7 - Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream", Higher Results Are Better "a", "b",207.6442,209.7847,208.7416 "c",211.1526,207.8217,206.9239 "d", "SVT-AV1 2.0 - Encoder Mode: Preset 4 - Input: Bosphorus 4K", Higher Results Are Better "a", "b",8.595,8.541,8.589 "c",8.45,8.518,8.484 "d", "SVT-AV1 2.0 - Encoder Mode: Preset 12 - Input: Bosphorus 4K", Higher Results Are Better "a", "b",159.117,160.64,169.101,162.711,164.304 "c",152.626,160.065,163.127,161.988,160.526,155.436,150.378,168.275,164.677,168.367,151.856,158.848,159.957,167.748,164.531 "d", "Primesieve 12.1 - Length: 1e13", Lower Results Are Better "a", "b",11.81,11.892,11.841 "c",11.888,11.874,11.85 "d", "SVT-AV1 2.0 - Encoder Mode: Preset 4 - Input: Bosphorus 1080p", Higher Results Are Better "a", "b",22.799,22.667,23.229 "c",23.549,23.843,23.029 "d", "SVT-AV1 2.0 - Encoder Mode: Preset 8 - Input: Bosphorus 4K", Higher Results Are Better "a", "b",92.911,90.765,90.187 "c",91.057,88.659,91.608 "d", "SVT-AV1 2.0 - Encoder Mode: Preset 13 - Input: Bosphorus 4K", Higher Results Are Better "a", "b",160.879,160.939,163.141 "c",163.995,155.917,162.193,165.279,162.717 "d", "SVT-AV1 2.0 - Encoder Mode: Preset 8 - Input: Bosphorus 1080p", Higher Results Are Better "a", "b",181.908,182.032,183.652 "c",182.819,181.495,188.082 "d", "SVT-AV1 2.0 - Encoder Mode: Preset 12 - Input: Bosphorus 1080p", Higher Results Are Better "a", "b",567.802,572.328,560.848 "c",578.641,564.856,561.131 "d", "SVT-AV1 2.0 - Encoder Mode: Preset 13 - Input: Bosphorus 1080p", Higher Results Are Better "a", "b",600.441,604.544,614.144 "c",592.915,596.933,575.503 "d", "Primesieve 12.1 - Length: 1e12", Lower Results Are Better "a", "b",1.158,1.183,1.152 "c",1.148,1.148,1.173 "d",