Geekbench ML Score

291
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 06 2024 10:14 PM
Views 1

System Information

System Information
Operating System Android 13
Model reeder S19 Max Pro S
Model IDreeder S19 Max Pro S
Motherboard ums9230_1h10
Governorschedutil
CPU Information
Name ARM Unisoc
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 3 part 3338 revision 1
Base Frequency 1.61 GHz
Cluster 18 Cores @ 1.61 GHz
Memory Information
Size 7.59 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 140
26.2 IPS
 
Image Classification (F16)
100% 141
26.3 IPS
 
Image Classification (I8)
97% 234
43.7 IPS
 
Image Segmentation (F32)
100% 206
3.44 IPS
 
Image Segmentation (F16)
100% 207
3.47 IPS
 
Image Segmentation (I8)
98% 253
4.23 IPS
 
Pose Estimation (F32)
100% 282
0.34 IPS
 
Pose Estimation (F16)
100% 275
0.33 IPS
 
Pose Estimation (I8)
100% 1302
1.58 IPS
 
Object Detection (F32)
100% 159
11.8 IPS
 
Object Detection (F16)
100% 157
11.7 IPS
 
Object Detection (I8)
61% 306
22.8 IPS
 
Face Detection (F32)
100% 336
4.00 IPS
 
Face Detection (F16)
100% 334
3.97 IPS
 
Face Detection (I8)
86% 709
8.43 IPS
 
Depth Estimation (F32)
100% 308
2.39 IPS
 
Depth Estimation (F16)
100% 306
2.38 IPS
 
Depth Estimation (I8)
95% 654
5.07 IPS
 
Style Transfer (F32)
100% 464
0.61 IPS
 
Style Transfer (F16)
100% 459
0.60 IPS
 
Style Transfer (I8)
98% 1376
1.81 IPS
 
Image Super-Resolution (F32)
100% 193
6.89 IPS
 
Image Super-Resolution (F16)
100% 188
6.71 IPS
 
Image Super-Resolution (I8)
98% 593
21.2 IPS
 
Text Classification (F32)
100% 179
256.8 IPS
 
Text Classification (F16)
100% 175
251.1 IPS
 
Text Classification (I8)
92% 142
204.3 IPS
 
Machine Translation (F32)
100% 321
5.91 IPS
 
Machine Translation (F16)
100% 311
5.73 IPS
 
Machine Translation (I8)
64% 169
3.11 IPS
 

Compare

Set Baseline Geekbench 6 now available