Geekbench ML Score

186
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 18 2024 03:25 PM
Views 2

System Information

System Information
Operating System Android 14
Model Samsung Galaxy A33
Model IDsamsung SM-A336E
Motherboard s5e8825
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 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 7.22 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 199
37.2 IPS
 
Image Classification (F16)
100% 206
38.5 IPS
 
Image Classification (I8)
97% 467
87.3 IPS
 
Image Segmentation (F32)
100% 273
4.56 IPS
 
Image Segmentation (F16)
100% 203
3.39 IPS
 
Image Segmentation (I8)
98% 232
3.88 IPS
 
Pose Estimation (F32)
100% 366
0.44 IPS
 
Pose Estimation (F16)
100% 375
0.45 IPS
 
Pose Estimation (I8)
100% 2224
2.69 IPS
 
Object Detection (F32)
100% 224
16.8 IPS
 
Object Detection (F16)
100% 246
18.4 IPS
 
Object Detection (I8)
61% 85
6.37 IPS
 
Face Detection (F32)
100% 233
2.77 IPS
 
Face Detection (F16)
100% 220
2.62 IPS
 
Face Detection (I8)
86% 288
3.42 IPS
 
Depth Estimation (F32)
100% 335
2.59 IPS
 
Depth Estimation (F16)
100% 265
2.05 IPS
 
Depth Estimation (I8)
95% 285
2.21 IPS
 
Style Transfer (F32)
100% 703
0.92 IPS
 
Style Transfer (F16)
100% 697
0.92 IPS
 
Style Transfer (I8)
98% 1747
2.30 IPS
 
Image Super-Resolution (F32)
100% 122
4.37 IPS
 
Image Super-Resolution (F16)
100% 182
6.50 IPS
 
Image Super-Resolution (I8)
98% 245
8.75 IPS
 
Text Classification (F32)
100% 10
14.1 IPS
 
Text Classification (F16)
100% 11
15.2 IPS
 
Text Classification (I8)
92% 11
16.1 IPS
 
Machine Translation (F32)
100% 24
0.45 IPS
 
Machine Translation (F16)
100% 68
1.25 IPS
 
Machine Translation (I8)
64% 104
1.91 IPS
 

Compare

Set Baseline Geekbench 6 now available