Geekbench ML Score

5275
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AVX2

Result Information

Upload Date October 09 2024 05:10 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% 3544
663.1 IPS
 
Image Classification (F16)
100% 3666
686.0 IPS
 
Image Classification (I8)
100% 2601
486.7 IPS
 
Image Segmentation (F32)
100% 5890
98.4 IPS
 
Image Segmentation (F16)
100% 5969
99.7 IPS
 
Image Segmentation (I8)
98% 4505
75.2 IPS
 
Pose Estimation (F32)
100% 19949
24.2 IPS
 
Pose Estimation (F16)
100% 19569
23.7 IPS
 
Pose Estimation (I8)
100% 16101
19.5 IPS
 
Object Detection (F32)
100% 2797
208.8 IPS
 
Object Detection (F16)
100% 2787
208.1 IPS
 
Object Detection (I8)
61% 2368
176.8 IPS
 
Face Detection (F32)
100% 7433
88.4 IPS
 
Face Detection (F16)
100% 7542
89.7 IPS
 
Face Detection (I8)
89% 5213
62.0 IPS
 
Depth Estimation (F32)
100% 16853
130.7 IPS
 
Depth Estimation (F16)
100% 16720
129.7 IPS
 
Depth Estimation (I8)
94% 14482
112.3 IPS
 
Style Transfer (F32)
100% 46366
61.0 IPS
 
Style Transfer (F16)
100% 47884
63.0 IPS
 
Style Transfer (I8)
98% 37640
49.5 IPS
 
Image Super-Resolution (F32)
100% 7443
265.8 IPS
 
Image Super-Resolution (F16)
100% 7495
267.7 IPS
 
Image Super-Resolution (I8)
99% 4894
174.8 IPS
 
Text Classification (F32)
100% 661
949.5 IPS
 
Text Classification (F16)
100% 641
921.1 IPS
 
Text Classification (I8)
98% 400
574.9 IPS
 
Machine Translation (F32)
100% 1431
26.3 IPS
 
Machine Translation (F16)
100% 1487
27.4 IPS
 
Machine Translation (I8)
70% 764
14.1 IPS
 

Compare

Set Baseline Geekbench 6 now available