Geekbench ML Score

2326
ONNX DirectML Inference Score
Geekbench ML 0.6.0 for Windows AArch64

Result Information

Upload Date August 29 2024 01:06 PM
Views 3

System Information

System Information
Operating System Microsoft Windows 11 Home (64-bit)
Model LENOVO 83ED
Motherboard LENOVO LNVNB161216
Power PlanBalanced
CPU Information
Name Snapdragon(R) X Elite - X1E78100 - Qualcomm(R) Oryon(TM) CPU
Topology 1 Processor, 12 Cores
Identifier ARMv8 (64-bit) Family 8 Model 1 Revision 201
Base Frequency 3.42 GHz
Cluster 18 Cores
Cluster 24 Cores
Memory Information
Size 16.00 GB
Inference Information
Framework ONNX
Backend DirectML
Device Snapdragon(R) X Elite - X1E78100 - Qualcomm(R) Adreno(TM) GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1502
281.0 IPS
 
Image Classification (F16)
100% 1473
275.7 IPS
 
Image Classification (I8)
100% 1215
227.4 IPS
 
Image Segmentation (F32)
100% 1683
28.1 IPS
 
Image Segmentation (F16)
100% 1663
27.8 IPS
 
Image Segmentation (I8)
98% 1473
24.6 IPS
 
Pose Estimation (F32)
100% 9493
11.5 IPS
 
Pose Estimation (F16)
100% 9454
11.4 IPS
 
Pose Estimation (I8)
100% 8458
10.2 IPS
 
Object Detection (F32)
100% 1221
91.2 IPS
 
Object Detection (F16)
100% 1235
92.2 IPS
 
Object Detection (I8)
71% 1091
81.5 IPS
 
Face Detection (F32)
100% 2743
32.6 IPS
 
Face Detection (F16)
100% 2864
34.1 IPS
 
Face Detection (I8)
93% 2272
27.0 IPS
 
Depth Estimation (F32)
100% 5518
42.8 IPS
 
Depth Estimation (F16)
100% 5541
43.0 IPS
 
Depth Estimation (I8)
94% 4569
35.4 IPS
 
Style Transfer (F32)
100% 12986
17.1 IPS
 
Style Transfer (F16)
100% 13178
17.3 IPS
 
Style Transfer (I8)
98% 11808
15.5 IPS
 
Image Super-Resolution (F32)
100% 4907
175.2 IPS
 
Image Super-Resolution (F16)
100% 4780
170.7 IPS
 
Image Super-Resolution (I8)
99% 3508
125.3 IPS
 
Text Classification (F32)
100% 297
427.4 IPS
 
Text Classification (F16)
100% 289
415.3 IPS
 
Text Classification (I8)
98% 251
360.6 IPS
 
Machine Translation (F32)
100% 1075
19.8 IPS
 
Machine Translation (F16)
100% 1085
20.0 IPS
 
Machine Translation (I8)
65% 695
12.8 IPS
 

Compare

Set Baseline Geekbench 6 now available