Geekbench ML Score

287
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 23 2022 07:23 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 CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 264
28.3 IPS
 
Image Classification (F16)
100% 219
23.4 IPS
 
Image Classification (I8)
81% 158
16.9 IPS
 
Image Segmentation (F32)
100% 474
2.93 IPS
 
Image Segmentation (F16)
100% 478
2.95 IPS
 
Image Segmentation (I8)
89% 756
4.67 IPS
 
Pose Estimation (F32)
100% 228
0.92 IPS
 
Pose Estimation (F16)
100% 228
0.92 IPS
 
Pose Estimation (I8)
80% 180
0.73 IPS
 
Object Detection (F32)
100% 220
7.70 IPS
 
Object Detection (F16)
100% 208
7.30 IPS
 
Object Detection (I8)
52% 210
7.38 IPS
 
Face Detection (F32)
100% 340
3.90 IPS
 
Face Detection (F16)
100% 408
4.68 IPS
 
Face Detection (I8)
75% 401
4.61 IPS
 
Text Classification (F32)
100% 230
90.8 IPS
 
Text Classification (F16)
100% 226
89.3 IPS
 
Machine Translation (F32)
100% 358
55.1 IPS
 
Machine Translation (F16)
100% 357
55.0 IPS
 

Compare

Set Baseline Geekbench 6 now available