Geekbench ML Score

867
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 18 2022 01:49 PM
Views 4

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 10.27 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 319
34.2 IPS
 
Image Classification (F16)
100% 724
77.5 IPS
 
Image Classification (I8)
80% 646
69.2 IPS
 
Image Segmentation (F32)
100% 1318
8.14 IPS
 
Image Segmentation (F16)
100% 3070
19.0 IPS
 
Image Segmentation (I8)
89% 2824
17.4 IPS
 
Pose Estimation (F32)
100% 459
1.86 IPS
 
Pose Estimation (F16)
100% 1132
4.58 IPS
 
Pose Estimation (I8)
80% 1114
4.51 IPS
 
Object Detection (F32)
100% 272
9.55 IPS
 
Object Detection (F16)
100% 510
17.9 IPS
 
Object Detection (I8)
54% 510
17.9 IPS
 
Face Detection (F32)
100% 1212
13.9 IPS
 
Face Detection (F16)
97% 2477
28.5 IPS
 
Face Detection (I8)
76% 2175
25.0 IPS
 
Text Classification (F32)
100% 296
116.9 IPS
 
Text Classification (F16)
98% 511
202.2 IPS
 
Machine Translation (F32)
100% 985
151.8 IPS
 
Machine Translation (F16)
100% 984
151.7 IPS
 

Compare

Set Baseline Geekbench 6 now available