Geekbench ML Score

882
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 14 2021 07:04 AM
Views 2

System Information

System Information
Operating System iOS 15.0.2
Model iPhone 12 Pro
Model IDiPhone13,3
Motherboard D53pAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.60 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 636
68.1 IPS
 
Image Classification (F16)
100% 614
65.8 IPS
 
Image Classification (I8)
81% 421
45.1 IPS
 
Image Segmentation (F32)
100% 968
5.98 IPS
 
Image Segmentation (F16)
100% 941
5.81 IPS
 
Image Segmentation (I8)
89% 1389
8.58 IPS
 
Pose Estimation (F32)
100% 361
1.46 IPS
 
Pose Estimation (F16)
100% 352
1.43 IPS
 
Pose Estimation (I8)
80% 432
1.75 IPS
 
Object Detection (F32)
100% 880
30.9 IPS
 
Object Detection (F16)
100% 876
30.7 IPS
 
Object Detection (I8)
52% 712
25.0 IPS
 
Face Detection (F32)
100% 1082
12.4 IPS
 
Face Detection (F16)
100% 1052
12.1 IPS
 
Face Detection (I8)
75% 812
9.32 IPS
 
Text Classification (F32)
100% 2413
954.4 IPS
 
Text Classification (F16)
100% 2331
922.0 IPS
 
Machine Translation (F32)
100% 1685
259.7 IPS
 
Machine Translation (F16)
100% 1678
258.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download