Geekbench ML Score

302
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 10 2024 07:16 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 NNAPI
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 118
22.1 IPS
 
Image Classification (F16)
100% 361
67.5 IPS
 
Image Classification (I8)
97% 71
13.3 IPS
 
Image Segmentation (F32)
100% 214
3.58 IPS
 
Image Segmentation (F16)
100% 377
6.29 IPS
 
Image Segmentation (I8)
98% 81
1.36 IPS
 
Pose Estimation (F32)
100% 759
0.92 IPS
 
Pose Estimation (F16)
100% 1830
2.22 IPS
 
Pose Estimation (I8)
80% 1116
1.35 IPS
 
Object Detection (F32)
100% 145
10.8 IPS
 
Object Detection (F16)
100% 287
21.4 IPS
 
Object Detection (I8)
51% 91
6.78 IPS
 
Face Detection (F32)
25% 545
6.48 IPS
 
Face Detection (F16)
25% 771
9.17 IPS
 
Face Detection (I8)
87% 127
1.50 IPS
 
Depth Estimation (F32)
100% 351
2.72 IPS
 
Depth Estimation (F16)
75% 438
3.40 IPS
 
Depth Estimation (I8)
93% 341
2.64 IPS
 
Style Transfer (F32)
100% 674
0.89 IPS
 
Style Transfer (F16)
100% 1107
1.46 IPS
 
Style Transfer (I8)
98% 1568
2.06 IPS
 
Image Super-Resolution (F32)
100% 361
12.9 IPS
 
Image Super-Resolution (F16)
100% 767
27.4 IPS
 
Image Super-Resolution (I8)
98% 409
14.6 IPS
 
Text Classification (F32)
100% 85
121.5 IPS
 
Text Classification (F16)
100% 94
135.7 IPS
 
Text Classification (I8)
94% 85
121.7 IPS
 
Machine Translation (F32)
100% 220
4.04 IPS
 
Machine Translation (F16)
100% 271
4.99 IPS
 
Machine Translation (I8)
57% 154
2.83 IPS
 

Compare

Set Baseline Geekbench 6 now available