Geekbench ML Score

460
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date May 15 2022 07:58 PM
Views 1

System Information

System Information
Operating System Android 12
Model Samsung Galaxy S20 FE 5G
Model IDsamsung SM-G781B
Motherboard kona
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 7.44 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 410
43.9 IPS
 
Image Classification (F16)
100% 454
48.6 IPS
 
Image Classification (I8)
81% 224
24.0 IPS
 
Image Segmentation (F32)
100% 698
4.31 IPS
 
Image Segmentation (F16)
100% 690
4.26 IPS
 
Image Segmentation (I8)
89% 961
5.93 IPS
 
Pose Estimation (F32)
100% 282
1.14 IPS
 
Pose Estimation (F16)
100% 281
1.14 IPS
 
Pose Estimation (I8)
80% 247
1.00 IPS
 
Object Detection (F32)
100% 502
17.6 IPS
 
Object Detection (F16)
100% 496
17.4 IPS
 
Object Detection (I8)
52% 359
12.6 IPS
 
Face Detection (F32)
100% 701
8.05 IPS
 
Face Detection (F16)
100% 691
7.94 IPS
 
Face Detection (I8)
75% 590
6.78 IPS
 
Text Classification (F32)
100% 356
140.8 IPS
 
Text Classification (F16)
100% 398
157.6 IPS
 
Machine Translation (F32)
100% 541
83.4 IPS
 
Machine Translation (F16)
100% 535
82.4 IPS
 

Compare

Set Baseline Geekbench 6 now available