Geekbench ML Score

677
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date November 03 2021 11:06 AM
Views 2

System Information

System Information
Operating System Android 11
Model Samsung Galaxy A51 5G
Model IDsamsung SM-A516N
Motherboard exynos980
Governorenergy_step
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3341 revision 0
Base Frequency 1.79 GHz
Cluster 16 Cores @ 1.79 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 5.20 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 383
41.1 IPS
 
Image Classification (F16)
100% 718
77.0 IPS
 
Image Classification (I8)
80% 654
70.1 IPS
 
Image Segmentation (F32)
100% 902
5.57 IPS
 
Image Segmentation (F16)
100% 1867
11.5 IPS
 
Image Segmentation (I8)
89% 1824
11.3 IPS
 
Pose Estimation (F32)
100% 201
0.81 IPS
 
Pose Estimation (F16)
100% 955
3.86 IPS
 
Pose Estimation (I8)
80% 945
3.82 IPS
 
Object Detection (F32)
100% 332
11.6 IPS
 
Object Detection (F16)
100% 491
17.2 IPS
 
Object Detection (I8)
54% 483
16.9 IPS
 
Face Detection (F32)
100% 808
9.28 IPS
 
Face Detection (F16)
97% 1791
20.6 IPS
 
Face Detection (I8)
75% 1545
17.8 IPS
 
Text Classification (F32)
100% 426
168.3 IPS
 
Text Classification (F16)
98% 592
234.0 IPS
 
Machine Translation (F32)
100% 376
57.9 IPS
 
Machine Translation (F16)
100% 368
56.7 IPS
 

Compare

Set Baseline Geekbench 6 now available