Geekbench ML Score

1492
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date August 14 2023 11:49 AM
Views 1

System Information

System Information
Operating System Android 13
Model Samsung Galaxy S21+ 5G
Model IDsamsung SM-G996N
Motherboard exynos2100
Governorenergy_step
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3396 revision 0
Base Frequency 2.21 GHz
Cluster 14 Cores @ 2.21 GHz
Cluster 23 Cores @ 2.81 GHz
Cluster 31 Core @ 2.91 GHz
Memory Information
Size 7.00 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1111
119.0 IPS
 
Image Classification (F16)
100% 1991
213.3 IPS
 
Image Classification (I8)
80% 1812
194.2 IPS
 
Image Segmentation (F32)
100% 2458
15.2 IPS
 
Image Segmentation (F16)
100% 4778
29.5 IPS
 
Image Segmentation (I8)
89% 4808
29.7 IPS
 
Pose Estimation (F32)
100% 703
2.84 IPS
 
Pose Estimation (F16)
100% 2539
10.3 IPS
 
Pose Estimation (I8)
80% 2524
10.2 IPS
 
Object Detection (F32)
100% 580
20.3 IPS
 
Object Detection (F16)
100% 759
26.6 IPS
 
Object Detection (I8)
54% 750
26.3 IPS
 
Face Detection (F32)
100% 1891
21.7 IPS
 
Face Detection (F16)
97% 3706
42.6 IPS
 
Face Detection (I8)
75% 3194
36.7 IPS
 
Text Classification (F32)
100% 911
360.2 IPS
 
Text Classification (F16)
98% 1194
472.4 IPS
 
Machine Translation (F32)
100% 497
76.6 IPS
 
Machine Translation (F16)
100% 493
76.0 IPS
 

Compare

Set Baseline Geekbench 6 now available