Geekbench ML Score

814
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 04:44 PM
Views 1

System Information

System Information
Operating System iOS 15.1.1
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% 566
60.6 IPS
 
Image Classification (F16)
100% 528
56.6 IPS
 
Image Classification (I8)
81% 411
44.0 IPS
 
Image Segmentation (F32)
100% 853
5.27 IPS
 
Image Segmentation (F16)
100% 817
5.05 IPS
 
Image Segmentation (I8)
89% 1310
8.09 IPS
 
Pose Estimation (F32)
100% 315
1.28 IPS
 
Pose Estimation (F16)
100% 304
1.23 IPS
 
Pose Estimation (I8)
80% 394
1.59 IPS
 
Object Detection (F32)
100% 789
27.7 IPS
 
Object Detection (F16)
100% 788
27.7 IPS
 
Object Detection (I8)
52% 723
25.4 IPS
 
Face Detection (F32)
100% 867
9.96 IPS
 
Face Detection (F16)
100% 907
10.4 IPS
 
Face Detection (I8)
75% 925
10.6 IPS
 
Text Classification (F32)
100% 2277
900.7 IPS
 
Text Classification (F16)
100% 2276
900.1 IPS
 
Machine Translation (F32)
100% 1680
259.0 IPS
 
Machine Translation (F16)
100% 1669
257.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download