Geekbench ML Score

237
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 06 2024 07:33 AM
Views 1

System Information

System Information
Operating System Android 13
Model Xiaomi 2201116SG
Model IDXiaomi 2201116SG
Motherboard veux
Governorschedutil
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3393 revision 1
Base Frequency 1.80 GHz
Cluster 16 Cores @ 1.80 GHz
Cluster 22 Cores @ 2.21 GHz
Memory Information
Size 7.26 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 106
19.9 IPS
 
Image Classification (F16)
100% 173
32.3 IPS
 
Image Classification (I8)
97% 184
34.4 IPS
 
Image Segmentation (F32)
100% 137
2.28 IPS
 
Image Segmentation (F16)
100% 241
4.02 IPS
 
Image Segmentation (I8)
98% 248
4.14 IPS
 
Pose Estimation (F32)
100% 211
0.26 IPS
 
Pose Estimation (F16)
100% 285
0.34 IPS
 
Pose Estimation (I8)
100% 285
0.34 IPS
 
Object Detection (F32)
100% 90
6.74 IPS
 
Object Detection (F16)
100% 125
9.35 IPS
 
Object Detection (I8)
62% 130
9.67 IPS
 
Face Detection (F32)
100% 251
2.98 IPS
 
Face Detection (F16)
97% 448
5.33 IPS
 
Face Detection (I8)
87% 458
5.45 IPS
 
Depth Estimation (F32)
100% 254
1.97 IPS
 
Depth Estimation (F16)
100% 436
3.38 IPS
 
Depth Estimation (I8)
95% 440
3.42 IPS
 
Style Transfer (F32)
100% 481
0.63 IPS
 
Style Transfer (F16)
100% 1018
1.34 IPS
 
Style Transfer (I8)
98% 1025
1.35 IPS
 
Image Super-Resolution (F32)
100% 127
4.53 IPS
 
Image Super-Resolution (F16)
100% 210
7.49 IPS
 
Image Super-Resolution (I8)
98% 212
7.59 IPS
 
Text Classification (F32)
100% 115
165.8 IPS
 
Text Classification (F16)
100% 116
166.0 IPS
 
Text Classification (I8)
92% 218
312.9 IPS
 
Machine Translation (F32)
100% 218
4.02 IPS
 
Machine Translation (F16)
100% 217
3.99 IPS
 
Machine Translation (I8)
64% 283
5.21 IPS
 

Compare

Set Baseline Geekbench 6 now available