Geekbench ML Score

573
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

Upload Date June 07 2023 02:36 PM
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 CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 593
63.5 IPS
 
Image Classification (F16)
100% 588
63.0 IPS
 
Image Classification (I8)
81% 227
24.3 IPS
 
Image Segmentation (F32)
100% 931
5.75 IPS
 
Image Segmentation (F16)
100% 913
5.64 IPS
 
Image Segmentation (I8)
89% 1111
6.87 IPS
 
Pose Estimation (F32)
100% 378
1.53 IPS
 
Pose Estimation (F16)
100% 369
1.49 IPS
 
Pose Estimation (I8)
80% 261
1.06 IPS
 
Object Detection (F32)
100% 467
16.4 IPS
 
Object Detection (F16)
100% 495
17.4 IPS
 
Object Detection (I8)
52% 401
14.1 IPS
 
Face Detection (F32)
100% 870
9.99 IPS
 
Face Detection (F16)
100% 1006
11.6 IPS
 
Face Detection (I8)
75% 688
7.90 IPS
 
Text Classification (F32)
100% 394
155.9 IPS
 
Text Classification (F16)
100% 372
147.0 IPS
 
Machine Translation (F32)
100% 1070
164.9 IPS
 
Machine Translation (F16)
100% 1092
168.3 IPS
 

Compare

Set Baseline Geekbench 6 now available