Geekbench ML Score

916
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date February 28 2022 07:21 PM
Views 5

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 10.27 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 325
34.8 IPS
 
Image Classification (F16)
100% 850
91.0 IPS
 
Image Classification (I8)
80% 726
77.8 IPS
 
Image Segmentation (F32)
100% 1255
7.75 IPS
 
Image Segmentation (F16)
100% 3139
19.4 IPS
 
Image Segmentation (I8)
89% 2946
18.2 IPS
 
Pose Estimation (F32)
100% 498
2.02 IPS
 
Pose Estimation (F16)
100% 1124
4.55 IPS
 
Pose Estimation (I8)
80% 1096
4.44 IPS
 
Object Detection (F32)
100% 272
9.55 IPS
 
Object Detection (F16)
100% 580
20.4 IPS
 
Object Detection (I8)
54% 548
19.2 IPS
 
Face Detection (F32)
100% 1237
14.2 IPS
 
Face Detection (F16)
97% 2899
33.3 IPS
 
Face Detection (I8)
76% 2369
27.2 IPS
 
Text Classification (F32)
100% 319
126.3 IPS
 
Text Classification (F16)
98% 604
239.0 IPS
 
Machine Translation (F32)
100% 982
151.4 IPS
 
Machine Translation (F16)
100% 968
149.3 IPS
 

Compare

Set Baseline Geekbench 6 now available