Geekbench ML Score

71
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date October 01 2024 12:46 PM
Views 1

System Information

System Information
Operating System Android 12
Model HUAWEI MAO-LX9
Model IDHUAWEI MAO-LX9
Motherboard MAO
Governorschedutil
CPU Information
Name ARM Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3337 revision 0
Base Frequency 1.90 GHz
Cluster 14 Cores @ 1.90 GHz
Cluster 24 Cores @ 2.40 GHz
Memory Information
Size 7.47 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 147
27.5 IPS
 
Image Classification (F16)
100% 144
27.0 IPS
 
Image Classification (I8)
97% 203
38.0 IPS
 
Image Segmentation (F32)
100% 195
3.26 IPS
 
Image Segmentation (F16)
100% 190
3.18 IPS
 
Image Segmentation (I8)
98% 79
1.31 IPS
 
Pose Estimation (F32)
100% 114
0.14 IPS
 
Pose Estimation (F16)
100% 114
0.14 IPS
 
Pose Estimation (I8)
100% 222
0.27 IPS
 
Object Detection (F32)
100% 35
2.58 IPS
 
Object Detection (F16)
100% 35
2.63 IPS
 
Object Detection (I8)
61% 48
3.56 IPS
 
Face Detection (F32)
100% 101
1.20 IPS
 
Face Detection (F16)
100% 102
1.21 IPS
 
Face Detection (I8)
86% 155
1.84 IPS
 
Depth Estimation (F32)
100% 95
0.74 IPS
 
Depth Estimation (F16)
100% 94
0.73 IPS
 
Depth Estimation (I8)
95% 142
1.10 IPS
 
Style Transfer (F32)
100% 211
0.28 IPS
 
Style Transfer (F16)
100% 212
0.28 IPS
 
Style Transfer (I8)
98% 440
0.58 IPS
 
Image Super-Resolution (F32)
100% 54
1.94 IPS
 
Image Super-Resolution (F16)
100% 53
1.91 IPS
 
Image Super-Resolution (I8)
98% 87
3.09 IPS
 
Text Classification (F32)
100% 7
10.3 IPS
 
Text Classification (F16)
100% 7
9.46 IPS
 
Text Classification (I8)
92% 8
10.9 IPS
 
Machine Translation (F32)
100% 16
0.30 IPS
 
Machine Translation (F16)
100% 16
0.30 IPS
 
Machine Translation (I8)
64% 18
0.34 IPS
 

Compare

Set Baseline Geekbench 6 now available