Geekbench ML Score

397
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date May 07 2024 02:11 AM
Views 1

System Information

System Information
Operating System Android 14
Model vivo I2208
Model IDvivo I2208
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 @ 2.02 GHz
Memory Information
Size 5.32 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 106
19.7 IPS
 
Image Classification (F16)
100% 191
35.7 IPS
 
Image Classification (I8)
97% 500
93.6 IPS
 
Image Segmentation (F32)
100% 273
4.57 IPS
 
Image Segmentation (F16)
100% 284
4.74 IPS
 
Image Segmentation (I8)
98% 391
6.54 IPS
 
Pose Estimation (F32)
100% 351
0.42 IPS
 
Pose Estimation (F16)
100% 336
0.41 IPS
 
Pose Estimation (I8)
100% 1894
2.29 IPS
 
Object Detection (F32)
100% 205
15.3 IPS
 
Object Detection (F16)
100% 210
15.6 IPS
 
Object Detection (I8)
61% 548
40.9 IPS
 
Face Detection (F32)
100% 433
5.15 IPS
 
Face Detection (F16)
100% 431
5.12 IPS
 
Face Detection (I8)
86% 1080
12.8 IPS
 
Depth Estimation (F32)
100% 416
3.22 IPS
 
Depth Estimation (F16)
100% 428
3.32 IPS
 
Depth Estimation (I8)
95% 1095
8.49 IPS
 
Style Transfer (F32)
100% 699
0.92 IPS
 
Style Transfer (F16)
100% 676
0.89 IPS
 
Style Transfer (I8)
98% 1640
2.16 IPS
 
Image Super-Resolution (F32)
100% 251
8.96 IPS
 
Image Super-Resolution (F16)
100% 249
8.88 IPS
 
Image Super-Resolution (I8)
98% 812
29.0 IPS
 
Text Classification (F32)
100% 226
324.5 IPS
 
Text Classification (F16)
100% 210
301.2 IPS
 
Text Classification (I8)
92% 182
261.4 IPS
 
Machine Translation (F32)
100% 474
8.72 IPS
 
Machine Translation (F16)
100% 448
8.24 IPS
 
Machine Translation (I8)
64% 205
3.78 IPS
 

Compare

Set Baseline Geekbench 6 now available