Geekbench ML Score

254
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date September 28 2021 08:23 PM
Views 1

System Information

System Information
Operating System Android 11
Model Samsung Galaxy S20 Ultra
Model IDsamsung SM-G988B
Motherboard exynos990
Governorenergy_step
CPU Information
Name ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 83 architecture 8 variant 1 part 4 revision 0
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.50 GHz
Cluster 32 Cores @ 2.73 GHz
Memory Information
Size 10.65 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 169
18.1 IPS
 
Image Classification (F16)
100% 172
18.4 IPS
 
Image Classification (I8)
81% 156
16.7 IPS
 
Image Segmentation (F32)
100% 364
2.25 IPS
 
Image Segmentation (F16)
100% 370
2.29 IPS
 
Image Segmentation (I8)
89% 655
4.05 IPS
 
Pose Estimation (F32)
100% 212
0.86 IPS
 
Pose Estimation (F16)
100% 213
0.86 IPS
 
Pose Estimation (I8)
80% 185
0.75 IPS
 
Object Detection (F32)
100% 202
7.08 IPS
 
Object Detection (F16)
100% 201
7.06 IPS
 
Object Detection (I8)
52% 232
8.13 IPS
 
Face Detection (F32)
100% 365
4.20 IPS
 
Face Detection (F16)
100% 353
4.06 IPS
 
Face Detection (I8)
75% 397
4.56 IPS
 
Text Classification (F32)
100% 182
72.0 IPS
 
Text Classification (F16)
100% 181
71.8 IPS
 
Machine Translation (F32)
100% 310
47.8 IPS
 
Machine Translation (F16)
100% 309
47.6 IPS
 

Compare

Set Baseline Geekbench 6 now available