Geekbench ML Score

438
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 08 2022 03:30 PM
Views 1

System Information

System Information
Operating System Android 12
Model Samsung Galaxy S20 5G
Model IDsamsung SM-G981N
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 10.35 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 460
49.3 IPS
 
Image Classification (F16)
100% 464
49.8 IPS
 
Image Classification (I8)
81% 190
20.4 IPS
 
Image Segmentation (F32)
100% 648
4.00 IPS
 
Image Segmentation (F16)
100% 636
3.93 IPS
 
Image Segmentation (I8)
89% 872
5.39 IPS
 
Pose Estimation (F32)
100% 266
1.08 IPS
 
Pose Estimation (F16)
100% 264
1.07 IPS
 
Pose Estimation (I8)
80% 244
0.99 IPS
 
Object Detection (F32)
100% 459
16.1 IPS
 
Object Detection (F16)
100% 417
14.6 IPS
 
Object Detection (I8)
52% 331
11.6 IPS
 
Face Detection (F32)
100% 611
7.02 IPS
 
Face Detection (F16)
100% 612
7.03 IPS
 
Face Detection (I8)
75% 543
6.24 IPS
 
Text Classification (F32)
100% 393
155.6 IPS
 
Text Classification (F16)
100% 397
156.9 IPS
 
Machine Translation (F32)
100% 560
86.2 IPS
 
Machine Translation (F16)
100% 554
85.3 IPS
 

Compare

Set Baseline