Geekbench ML Score

442
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date January 19 2022 08:50 AM
Views 2

System Information

System Information
Operating System Android 11
Model samsung SM-A525F
Model IDsamsung SM-A525F
Motherboard atoll
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 15 part 2052 revision 15
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.32 GHz
Memory Information
Size 5.37 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 310
33.2 IPS
 
Image Classification (F16)
100% 535
57.3 IPS
 
Image Classification (I8)
80% 471
50.5 IPS
 
Image Segmentation (F32)
100% 705
4.35 IPS
 
Image Segmentation (F16)
100% 1339
8.27 IPS
 
Image Segmentation (I8)
89% 1175
7.26 IPS
 
Pose Estimation (F32)
100% 353
1.43 IPS
 
Pose Estimation (F16)
100% 686
2.78 IPS
 
Pose Estimation (I8)
80% 681
2.75 IPS
 
Object Detection (F32)
100% 178
6.26 IPS
 
Object Detection (F16)
99% 222
7.80 IPS
 
Object Detection (I8)
53% 219
7.67 IPS
 
Face Detection (F32)
100% 628
7.22 IPS
 
Face Detection (F16)
97% 1060
12.2 IPS
 
Face Detection (I8)
76% 895
10.3 IPS
 
Text Classification (F32)
100% 203
80.4 IPS
 
Text Classification (F16)
98% 248
98.1 IPS
 
Machine Translation (F32)
100% 224
34.5 IPS
 
Machine Translation (F16)
100% 224
34.5 IPS
 

Compare

Set Baseline Geekbench 6 now available