Geekbench ML Score

197
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date September 06 2024 11:26 PM
Views 2

System Information

System Information
Operating System Android 14
Model OPPO PKD130
Model IDOPPO PKD130
Motherboard k6835v2_64
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 4 part 3339 revision 0
Base Frequency 2.00 GHz
Cluster 16 Cores @ 2.00 GHz
Cluster 22 Cores @ 2.40 GHz
Memory Information
Size 7.41 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 99
18.6 IPS
 
Image Classification (F16)
100% 174
32.5 IPS
 
Image Classification (I8)
97% 166
31.1 IPS
 
Image Segmentation (F32)
100% 136
2.26 IPS
 
Image Segmentation (F16)
100% 244
4.08 IPS
 
Image Segmentation (I8)
98% 238
3.98 IPS
 
Pose Estimation (F32)
100% 93
0.11 IPS
 
Pose Estimation (F16)
100% 112
0.14 IPS
 
Pose Estimation (I8)
100% 112
0.14 IPS
 
Object Detection (F32)
100% 79
5.90 IPS
 
Object Detection (F16)
100% 125
9.36 IPS
 
Object Detection (I8)
62% 125
9.30 IPS
 
Face Detection (F32)
100% 309
3.67 IPS
 
Face Detection (F16)
98% 432
5.14 IPS
 
Face Detection (I8)
86% 420
4.99 IPS
 
Depth Estimation (F32)
100% 187
1.45 IPS
 
Depth Estimation (F16)
100% 243
1.88 IPS
 
Depth Estimation (I8)
95% 241
1.87 IPS
 
Style Transfer (F32)
100% 363
0.48 IPS
 
Style Transfer (F16)
100% 512
0.67 IPS
 
Style Transfer (I8)
98% 512
0.67 IPS
 
Image Super-Resolution (F32)
100% 98
3.51 IPS
 
Image Super-Resolution (F16)
100% 153
5.46 IPS
 
Image Super-Resolution (I8)
98% 151
5.39 IPS
 
Text Classification (F32)
100% 158
227.8 IPS
 
Text Classification (F16)
100% 159
227.9 IPS
 
Text Classification (I8)
92% 259
372.5 IPS
 
Machine Translation (F32)
100% 288
5.30 IPS
 
Machine Translation (F16)
100% 290
5.34 IPS
 
Machine Translation (I8)
64% 311
5.73 IPS
 

Compare

Set Baseline Geekbench 6 now available