Geekbench ML Score

3090
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 31 2022 11:15 AM
Views 5

System Information

System Information
Operating System Android 12
Model Sony XQ-CT54
Model IDSony XQ-CT54
Motherboard taro
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 2 part 3400 revision 0
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.50 GHz
Cluster 31 Core @ 3.00 GHz
Memory Information
Size 10.81 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1275
136.7 IPS
 
Image Classification (F16)
100% 9430
1.01 KIPS
 
Image Classification (I8)
80% 22858
2.45 KIPS
 
Image Segmentation (F32)
100% 2767
17.1 IPS
 
Image Segmentation (F16)
100% 7447
46.0 IPS
 
Image Segmentation (I8)
89% 43002
265.6 IPS
 
Pose Estimation (F32)
100% 602
2.44 IPS
 
Pose Estimation (F16)
100% 10518
42.6 IPS
 
Pose Estimation (I8)
80% 54641
221.1 IPS
 
Object Detection (F32)
100% 1021
35.8 IPS
 
Object Detection (F16)
100% 1781
62.5 IPS
 
Object Detection (I8)
53% 1980
69.5 IPS
 
Face Detection (F32)
100% 1963
22.5 IPS
 
Face Detection (F16)
97% 7077
81.3 IPS
 
Face Detection (I8)
76% 49153
564.7 IPS
 
Text Classification (F32)
100% 17
6.65 IPS
 
Text Classification (F16)
100% 579
228.8 IPS
 
Machine Translation (F32)
100% 1002
154.4 IPS
 
Machine Translation (F16)
100% 1003
154.6 IPS
 

Compare

Set Baseline Geekbench 6 now available