Geekbench ML Score

681
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 23 2022 07:43 AM
Views 1

System Information

System Information
Operating System Android 13
Model Samsung Galaxy S21 Ultra 5G
Model IDsamsung SM-G998B
Motherboard exynos2100
Governorenergy_step
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 2.21 GHz
Cluster 14 Cores @ 2.21 GHz
Cluster 23 Cores @ 2.81 GHz
Cluster 31 Core @ 2.91 GHz
Memory Information
Size 10.33 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 386
41.4 IPS
 
Image Classification (F16)
100% 367
39.3 IPS
 
Image Classification (I8)
81% 376
40.2 IPS
 
Image Segmentation (F32)
100% 594
3.67 IPS
 
Image Segmentation (F16)
100% 600
3.71 IPS
 
Image Segmentation (I8)
89% 1779
11.0 IPS
 
Pose Estimation (F32)
100% 457
1.85 IPS
 
Pose Estimation (F16)
100% 1835
7.43 IPS
 
Pose Estimation (I8)
80% 1877
7.60 IPS
 
Object Detection (F32)
100% 575
20.2 IPS
 
Object Detection (F16)
99% 911
32.0 IPS
 
Object Detection (I8)
52% 424
14.9 IPS
 
Face Detection (F32)
100% 537
6.17 IPS
 
Face Detection (F16)
100% 526
6.04 IPS
 
Face Detection (I8)
75% 490
5.63 IPS
 
Text Classification (F32)
100% 941
372.0 IPS
 
Text Classification (F16)
100% 951
376.0 IPS
 
Machine Translation (F32)
100% 689
106.2 IPS
 
Machine Translation (F16)
100% 682
105.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download