Geekbench ML Score

183
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 10 2024 07:25 PM
Views 1

System Information

System Information
Operating System Android 14
Model samsung SM-X115
Model IDsamsung SM-X115
Motherboard gta9
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.20 GHz
Memory Information
Size 3.53 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 93
17.3 IPS
 
Image Classification (F16)
100% 163
30.4 IPS
 
Image Classification (I8)
97% 152
28.4 IPS
 
Image Segmentation (F32)
100% 122
2.04 IPS
 
Image Segmentation (F16)
100% 209
3.49 IPS
 
Image Segmentation (I8)
98% 214
3.58 IPS
 
Pose Estimation (F32)
100% 89
0.11 IPS
 
Pose Estimation (F16)
100% 105
0.13 IPS
 
Pose Estimation (I8)
100% 105
0.13 IPS
 
Object Detection (F32)
100% 79
5.89 IPS
 
Object Detection (F16)
100% 129
9.62 IPS
 
Object Detection (I8)
62% 116
8.69 IPS
 
Face Detection (F32)
100% 276
3.28 IPS
 
Face Detection (F16)
98% 395
4.70 IPS
 
Face Detection (I8)
86% 376
4.47 IPS
 
Depth Estimation (F32)
100% 174
1.35 IPS
 
Depth Estimation (F16)
100% 225
1.75 IPS
 
Depth Estimation (I8)
95% 225
1.74 IPS
 
Style Transfer (F32)
100% 344
0.45 IPS
 
Style Transfer (F16)
100% 478
0.63 IPS
 
Style Transfer (I8)
98% 478
0.63 IPS
 
Image Super-Resolution (F32)
100% 92
3.27 IPS
 
Image Super-Resolution (F16)
100% 141
5.03 IPS
 
Image Super-Resolution (I8)
98% 141
5.03 IPS
 
Text Classification (F32)
100% 146
209.6 IPS
 
Text Classification (F16)
100% 147
211.5 IPS
 
Text Classification (I8)
92% 234
336.9 IPS
 
Machine Translation (F32)
100% 274
5.04 IPS
 
Machine Translation (F16)
100% 270
4.97 IPS
 
Machine Translation (I8)
64% 274
5.05 IPS
 

Compare

Set Baseline Geekbench 6 now available