Geekbench ML Score

439
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 27 2024 07:10 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 CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 197
36.9 IPS
 
Image Classification (F16)
100% 185
34.6 IPS
 
Image Classification (I8)
97% 556
104.1 IPS
 
Image Segmentation (F32)
100% 275
4.60 IPS
 
Image Segmentation (F16)
100% 281
4.69 IPS
 
Image Segmentation (I8)
98% 461
7.70 IPS
 
Pose Estimation (F32)
100% 386
0.47 IPS
 
Pose Estimation (F16)
100% 389
0.47 IPS
 
Pose Estimation (I8)
100% 1900
2.30 IPS
 
Object Detection (F32)
100% 217
16.2 IPS
 
Object Detection (F16)
100% 221
16.5 IPS
 
Object Detection (I8)
61% 553
41.3 IPS
 
Face Detection (F32)
100% 432
5.14 IPS
 
Face Detection (F16)
100% 433
5.15 IPS
 
Face Detection (I8)
86% 1165
13.9 IPS
 
Depth Estimation (F32)
100% 431
3.34 IPS
 
Depth Estimation (F16)
100% 447
3.46 IPS
 
Depth Estimation (I8)
95% 994
7.71 IPS
 
Style Transfer (F32)
100% 729
0.96 IPS
 
Style Transfer (F16)
100% 735
0.97 IPS
 
Style Transfer (I8)
98% 1837
2.42 IPS
 
Image Super-Resolution (F32)
100% 266
9.50 IPS
 
Image Super-Resolution (F16)
100% 286
10.2 IPS
 
Image Super-Resolution (I8)
98% 947
33.8 IPS
 
Text Classification (F32)
100% 257
368.8 IPS
 
Text Classification (F16)
100% 256
368.6 IPS
 
Text Classification (I8)
92% 245
352.0 IPS
 
Machine Translation (F32)
100% 512
9.42 IPS
 
Machine Translation (F16)
100% 505
9.30 IPS
 
Machine Translation (I8)
64% 280
5.15 IPS
 

Compare

Set Baseline Geekbench 6 now available