Geekbench ML Score

251
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 27 2024 07:17 AM
Views 1

System Information

System Information
Operating System Android 14
Model vivo V2303
Model IDvivo V2303
Motherboard holi
Governorschedutil
CPU Information
Name ARM Qualcomm
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 7.27 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 108
20.1 IPS
 
Image Classification (F16)
100% 178
33.3 IPS
 
Image Classification (I8)
97% 190
35.5 IPS
 
Image Segmentation (F32)
100% 138
2.30 IPS
 
Image Segmentation (F16)
100% 247
4.12 IPS
 
Image Segmentation (I8)
98% 262
4.38 IPS
 
Pose Estimation (F32)
100% 210
0.25 IPS
 
Pose Estimation (F16)
100% 281
0.34 IPS
 
Pose Estimation (I8)
100% 278
0.34 IPS
 
Object Detection (F32)
100% 89
6.63 IPS
 
Object Detection (F16)
100% 127
9.45 IPS
 
Object Detection (I8)
62% 137
10.3 IPS
 
Face Detection (F32)
100% 258
3.06 IPS
 
Face Detection (F16)
97% 466
5.54 IPS
 
Face Detection (I8)
87% 479
5.70 IPS
 
Depth Estimation (F32)
100% 252
1.95 IPS
 
Depth Estimation (F16)
100% 430
3.34 IPS
 
Depth Estimation (I8)
95% 428
3.32 IPS
 
Style Transfer (F32)
100% 477
0.63 IPS
 
Style Transfer (F16)
100% 1017
1.34 IPS
 
Style Transfer (I8)
98% 1019
1.34 IPS
 
Image Super-Resolution (F32)
100% 123
4.40 IPS
 
Image Super-Resolution (F16)
100% 209
7.47 IPS
 
Image Super-Resolution (I8)
98% 213
7.62 IPS
 
Text Classification (F32)
100% 151
217.1 IPS
 
Text Classification (F16)
100% 151
217.0 IPS
 
Text Classification (I8)
92% 291
417.6 IPS
 
Machine Translation (F32)
100% 278
5.11 IPS
 
Machine Translation (F16)
100% 278
5.11 IPS
 
Machine Translation (I8)
64% 341
6.28 IPS
 

Compare

Set Baseline Geekbench 6 now available