Geekbench ML Score

5206
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 09 2024 05:12 PM
Views 2

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model LENOVO 83HM
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name Intel(R) Core(TM) Ultra 7 256V
Topology 1 Processor, 8 Cores
Identifier GenuineIntel Family 6 Model 189 Stepping 1
Base Frequency 2.20 GHz
Cluster 14 Cores
Cluster 24 Cores
L1 Instruction Cache64.0 KB x 4
L1 Data Cache48.0 KB x 4
L2 Cache2.50 MB x 1
L3 Cache12.0 MB x 1
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Intel(R) Arc(TM) 140V GPU (8GB)

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 3414
638.8 IPS
 
Image Classification (F16)
100% 3622
677.9 IPS
 
Image Classification (I8)
100% 2640
494.0 IPS
 
Image Segmentation (F32)
100% 5882
98.2 IPS
 
Image Segmentation (F16)
100% 5819
97.2 IPS
 
Image Segmentation (I8)
98% 4452
74.4 IPS
 
Pose Estimation (F32)
100% 19572
23.7 IPS
 
Pose Estimation (F16)
100% 19541
23.7 IPS
 
Pose Estimation (I8)
100% 15885
19.2 IPS
 
Object Detection (F32)
100% 2826
211.0 IPS
 
Object Detection (F16)
100% 2870
214.3 IPS
 
Object Detection (I8)
61% 2477
184.9 IPS
 
Face Detection (F32)
100% 7712
91.7 IPS
 
Face Detection (F16)
100% 7704
91.6 IPS
 
Face Detection (I8)
89% 5044
60.0 IPS
 
Depth Estimation (F32)
100% 16831
130.5 IPS
 
Depth Estimation (F16)
100% 17713
137.4 IPS
 
Depth Estimation (I8)
94% 14189
110.0 IPS
 
Style Transfer (F32)
100% 47007
61.8 IPS
 
Style Transfer (F16)
100% 47222
62.1 IPS
 
Style Transfer (I8)
98% 38128
50.2 IPS
 
Image Super-Resolution (F32)
100% 7048
251.7 IPS
 
Image Super-Resolution (F16)
100% 7370
263.2 IPS
 
Image Super-Resolution (I8)
99% 4681
167.2 IPS
 
Text Classification (F32)
100% 531
763.3 IPS
 
Text Classification (F16)
100% 562
807.9 IPS
 
Text Classification (I8)
98% 410
589.0 IPS
 
Machine Translation (F32)
100% 1468
27.0 IPS
 
Machine Translation (F16)
100% 1462
26.9 IPS
 
Machine Translation (I8)
70% 755
13.9 IPS
 

Compare

Set Baseline Geekbench 6 now available