Geekbench ML Score

792
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date July 16 2022 03:30 PM
Views 1

System Information

System Information
Operating System Android 10
Model samsung SM-G965F
Model IDsamsung SM-G965F
Motherboard exynos9810
Governorschedutil
CPU Information
Name ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 83 architecture 8 variant 1 part 2 revision 0
Base Frequency 1.79 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 24 Cores @ 2.70 GHz
Memory Information
Size 5.49 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 382
41.0 IPS
 
Image Classification (F16)
100% 636
68.1 IPS
 
Image Classification (I8)
81% 597
64.0 IPS
 
Image Segmentation (F32)
100% 786
4.86 IPS
 
Image Segmentation (F16)
100% 2773
17.1 IPS
 
Image Segmentation (I8)
89% 2649
16.4 IPS
 
Pose Estimation (F32)
100% 285
1.15 IPS
 
Pose Estimation (F16)
0% 1040
4.21 IPS
 
Pose Estimation (I8)
0% 1038
4.20 IPS
 
Object Detection (F32)
100% 282
9.91 IPS
 
Object Detection (F16)
99% 606
21.3 IPS
 
Object Detection (I8)
54% 544
19.1 IPS
 
Face Detection (F32)
100% 1190
13.7 IPS
 
Face Detection (F16)
97% 2330
26.8 IPS
 
Face Detection (I8)
75% 2010
23.1 IPS
 
Text Classification (F32)
100% 587
232.2 IPS
 
Text Classification (F16)
98% 926
366.2 IPS
 
Machine Translation (F32)
100% 414
63.8 IPS
 
Machine Translation (F16)
100% 402
62.0 IPS
 

Compare

Set Baseline