Geekbench ML Score

859
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 14 2021 07:07 AM
Views 1

System Information

System Information
Operating System iOS 15.0.1
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% 622
66.7 IPS
 
Image Classification (F16)
100% 585
62.7 IPS
 
Image Classification (I8)
81% 412
44.2 IPS
 
Image Segmentation (F32)
100% 940
5.81 IPS
 
Image Segmentation (F16)
100% 905
5.59 IPS
 
Image Segmentation (I8)
89% 1374
8.49 IPS
 
Pose Estimation (F32)
100% 345
1.39 IPS
 
Pose Estimation (F16)
100% 341
1.38 IPS
 
Pose Estimation (I8)
80% 423
1.71 IPS
 
Object Detection (F32)
100% 872
30.6 IPS
 
Object Detection (F16)
100% 863
30.3 IPS
 
Object Detection (I8)
52% 728
25.5 IPS
 
Face Detection (F32)
100% 1044
12.0 IPS
 
Face Detection (F16)
100% 1010
11.6 IPS
 
Face Detection (I8)
75% 809
9.30 IPS
 
Text Classification (F32)
100% 2144
847.9 IPS
 
Text Classification (F16)
100% 2266
896.3 IPS
 
Machine Translation (F32)
100% 1697
261.5 IPS
 
Machine Translation (F16)
100% 1694
261.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download