Geekbench ML Score

893
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date October 15 2022 02:19 PM
Views 1

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% 328
35.1 IPS
 
Image Classification (F16)
100% 841
90.1 IPS
 
Image Classification (I8)
80% 718
76.9 IPS
 
Image Segmentation (F32)
100% 1052
6.50 IPS
 
Image Segmentation (F16)
100% 2959
18.3 IPS
 
Image Segmentation (I8)
89% 2840
17.5 IPS
 
Pose Estimation (F32)
100% 503
2.03 IPS
 
Pose Estimation (F16)
100% 1120
4.53 IPS
 
Pose Estimation (I8)
80% 1131
4.57 IPS
 
Object Detection (F32)
100% 278
9.75 IPS
 
Object Detection (F16)
100% 546
19.1 IPS
 
Object Detection (I8)
54% 549
19.3 IPS
 
Face Detection (F32)
100% 1240
14.2 IPS
 
Face Detection (F16)
97% 2660
30.6 IPS
 
Face Detection (I8)
76% 2275
26.1 IPS
 
Text Classification (F32)
100% 322
127.4 IPS
 
Text Classification (F16)
98% 552
218.3 IPS
 
Machine Translation (F32)
100% 970
149.5 IPS
 
Machine Translation (F16)
100% 970
149.4 IPS
 

Compare

Set Baseline Geekbench 6 now available