Geekbench ML Score

343
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date December 09 2022 05:50 AM
Views 6

System Information

System Information
Operating System Android 10
Model Samsung Galaxy Tab S6
Model IDsamsung SM-T860
Motherboard msmnile
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 13 part 2052 revision 14
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 5.32 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 308
33.0 IPS
 
Image Classification (F16)
100% 246
26.4 IPS
 
Image Classification (I8)
81% 173
18.6 IPS
 
Image Segmentation (F32)
100% 488
3.02 IPS
 
Image Segmentation (F16)
100% 491
3.04 IPS
 
Image Segmentation (I8)
89% 783
4.84 IPS
 
Pose Estimation (F32)
100% 219
0.89 IPS
 
Pose Estimation (F16)
100% 207
0.84 IPS
 
Pose Estimation (I8)
80% 201
0.81 IPS
 
Object Detection (F32)
100% 353
12.4 IPS
 
Object Detection (F16)
100% 354
12.4 IPS
 
Object Detection (I8)
52% 272
9.56 IPS
 
Face Detection (F32)
100% 538
6.18 IPS
 
Face Detection (F16)
100% 521
5.99 IPS
 
Face Detection (I8)
75% 479
5.51 IPS
 
Text Classification (F32)
100% 290
114.7 IPS
 
Text Classification (F16)
100% 288
113.7 IPS
 
Machine Translation (F32)
100% 427
65.8 IPS
 
Machine Translation (F16)
100% 427
65.9 IPS
 

Compare

Set Baseline Geekbench 6 now available