Geekbench ML Score

2387
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 04 2023 01:30 AM
Views 2

System Information

System Information
Operating System Android 13
Model samsung SM-S918U
Model IDsamsung SM-S918U
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.36 GHz
Memory Information
Size 6.91 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1713
183.5 IPS
 
Image Classification (F16)
100% 2434
260.8 IPS
 
Image Classification (I8)
80% 2401
257.2 IPS
 
Image Segmentation (F32)
100% 5278
32.6 IPS
 
Image Segmentation (F16)
100% 9674
59.8 IPS
 
Image Segmentation (I8)
89% 8356
51.6 IPS
 
Pose Estimation (F32)
100% 2349
9.51 IPS
 
Pose Estimation (F16)
100% 4800
19.4 IPS
 
Pose Estimation (I8)
80% 4804
19.4 IPS
 
Object Detection (F32)
100% 1009
35.4 IPS
 
Object Detection (F16)
99% 1180
41.4 IPS
 
Object Detection (I8)
53% 1065
37.4 IPS
 
Face Detection (F32)
100% 3285
37.7 IPS
 
Face Detection (F16)
97% 5630
64.7 IPS
 
Face Detection (I8)
75% 5289
60.8 IPS
 
Text Classification (F32)
100% 701
277.1 IPS
 
Text Classification (F16)
98% 786
310.8 IPS
 
Machine Translation (F32)
100% 971
149.7 IPS
 
Machine Translation (F16)
100% 987
152.1 IPS
 

Compare

Set Baseline Geekbench 6 now available