Geekbench ML Score

821
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 04 2022 10:04 AM
Views 2

System Information

System Information
Operating System Android 12
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% 308
33.0 IPS
 
Image Classification (F16)
100% 774
82.9 IPS
 
Image Classification (I8)
80% 640
68.6 IPS
 
Image Segmentation (F32)
100% 1050
6.49 IPS
 
Image Segmentation (F16)
100% 2889
17.8 IPS
 
Image Segmentation (I8)
89% 2821
17.4 IPS
 
Pose Estimation (F32)
100% 433
1.75 IPS
 
Pose Estimation (F16)
100% 1082
4.38 IPS
 
Pose Estimation (I8)
80% 1057
4.28 IPS
 
Object Detection (F32)
100% 220
7.73 IPS
 
Object Detection (F16)
100% 487
17.1 IPS
 
Object Detection (I8)
54% 472
16.6 IPS
 
Face Detection (F32)
100% 1169
13.4 IPS
 
Face Detection (F16)
97% 2369
27.2 IPS
 
Face Detection (I8)
76% 2054
23.6 IPS
 
Text Classification (F32)
100% 277
109.4 IPS
 
Text Classification (F16)
98% 500
197.8 IPS
 
Machine Translation (F32)
100% 962
148.2 IPS
 
Machine Translation (F16)
100% 973
149.9 IPS
 

Compare

Set Baseline Geekbench 6 now available