Geekbench ML Score

239
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date January 27 2024 09:25 AM
Views 3

System Information

System Information
Operating System Android 13
Model vivo I2223
Model IDvivo I2223
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 7.28 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 104
19.5 IPS
 
Image Classification (F16)
100% 171
32.0 IPS
 
Image Classification (I8)
97% 184
34.5 IPS
 
Image Segmentation (F32)
100% 126
2.11 IPS
 
Image Segmentation (F16)
100% 204
3.40 IPS
 
Image Segmentation (I8)
98% 193
3.23 IPS
 
Pose Estimation (F32)
100% 209
0.25 IPS
 
Pose Estimation (F16)
100% 281
0.34 IPS
 
Pose Estimation (I8)
100% 271
0.33 IPS
 
Object Detection (F32)
100% 82
6.12 IPS
 
Object Detection (F16)
100% 122
9.09 IPS
 
Object Detection (I8)
62% 118
8.82 IPS
 
Face Detection (F32)
100% 249
2.96 IPS
 
Face Detection (F16)
97% 445
5.29 IPS
 
Face Detection (I8)
87% 458
5.44 IPS
 
Depth Estimation (F32)
100% 250
1.94 IPS
 
Depth Estimation (F16)
100% 425
3.29 IPS
 
Depth Estimation (I8)
95% 432
3.35 IPS
 
Style Transfer (F32)
100% 476
0.63 IPS
 
Style Transfer (F16)
100% 1013
1.33 IPS
 
Style Transfer (I8)
98% 1011
1.33 IPS
 
Image Super-Resolution (F32)
100% 126
4.52 IPS
 
Image Super-Resolution (F16)
100% 199
7.10 IPS
 
Image Super-Resolution (I8)
98% 205
7.31 IPS
 
Text Classification (F32)
100% 148
212.3 IPS
 
Text Classification (F16)
100% 148
212.6 IPS
 
Text Classification (I8)
92% 288
413.2 IPS
 
Machine Translation (F32)
100% 271
4.99 IPS
 
Machine Translation (F16)
100% 271
4.98 IPS
 
Machine Translation (I8)
64% 294
5.42 IPS
 

Compare

Set Baseline Geekbench 6 now available