Geekbench ML Score

385
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 02 2023 11:34 AM
Views 1

System Information

System Information
Operating System Android 13
Model samsung SM-S908B
Model IDsamsung SM-S908B
Motherboard s5e9925
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.82 GHz
Cluster 14 Cores @ 1.82 GHz
Cluster 23 Cores @ 2.52 GHz
Cluster 31 Core @ 2.80 GHz
Memory Information
Size 7.12 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 149
16.0 IPS
 
Image Classification (F16)
100% 387
41.5 IPS
 
Image Classification (I8)
80% 339
36.4 IPS
 
Image Segmentation (F32)
100% 639
3.95 IPS
 
Image Segmentation (F16)
100% 1430
8.83 IPS
 
Image Segmentation (I8)
89% 1320
8.15 IPS
 
Pose Estimation (F32)
100% 225
0.91 IPS
 
Pose Estimation (F16)
100% 491
1.99 IPS
 
Pose Estimation (I8)
80% 481
1.95 IPS
 
Object Detection (F32)
100% 137
4.79 IPS
 
Object Detection (F16)
100% 291
10.2 IPS
 
Object Detection (I8)
54% 296
10.4 IPS
 
Face Detection (F32)
100% 421
4.84 IPS
 
Face Detection (F16)
97% 919
10.6 IPS
 
Face Detection (I8)
76% 782
8.99 IPS
 
Text Classification (F32)
100% 103
40.6 IPS
 
Text Classification (F16)
98% 188
74.2 IPS
 
Machine Translation (F32)
100% 423
65.2 IPS
 
Machine Translation (F16)
100% 365
56.2 IPS
 

Compare

Set Baseline Geekbench 6 now available