Geekbench ML Score

422
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 17 2024 05:06 PM
Views 1

System Information

System Information
Operating System Android 14
Model samsung SM-A356E
Model IDsamsung SM-A356E
Motherboard s5e8835
Governorenergy_aware
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 2.00 GHz
Cluster 14 Cores @ 2.00 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 7.26 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 246
46.1 IPS
 
Image Classification (F16)
100% 181
33.9 IPS
 
Image Classification (I8)
97% 169
31.5 IPS
 
Image Segmentation (F32)
100% 255
4.26 IPS
 
Image Segmentation (F16)
100% 225
3.76 IPS
 
Image Segmentation (I8)
98% 340
5.69 IPS
 
Pose Estimation (F32)
100% 480
0.58 IPS
 
Pose Estimation (F16)
100% 468
0.57 IPS
 
Pose Estimation (I8)
100% 2909
3.52 IPS
 
Object Detection (F32)
100% 288
21.5 IPS
 
Object Detection (F16)
100% 311
23.2 IPS
 
Object Detection (I8)
61% 494
36.9 IPS
 
Face Detection (F32)
100% 389
4.63 IPS
 
Face Detection (F16)
100% 333
3.96 IPS
 
Face Detection (I8)
86% 601
7.14 IPS
 
Depth Estimation (F32)
100% 492
3.81 IPS
 
Depth Estimation (F16)
100% 429
3.33 IPS
 
Depth Estimation (I8)
95% 796
6.17 IPS
 
Style Transfer (F32)
100% 875
1.15 IPS
 
Style Transfer (F16)
100% 845
1.11 IPS
 
Style Transfer (I8)
98% 2278
3.00 IPS
 
Image Super-Resolution (F32)
100% 333
11.9 IPS
 
Image Super-Resolution (F16)
100% 345
12.3 IPS
 
Image Super-Resolution (I8)
98% 819
29.2 IPS
 
Text Classification (F32)
100% 347
498.9 IPS
 
Text Classification (F16)
100% 350
503.7 IPS
 
Text Classification (I8)
92% 313
450.1 IPS
 
Machine Translation (F32)
100% 346
6.37 IPS
 
Machine Translation (F16)
100% 485
8.92 IPS
 
Machine Translation (I8)
64% 108
1.99 IPS
 

Compare

Set Baseline Geekbench 6 now available