Geekbench ML Score

867
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 14 2021 07:05 AM
Views 1

System Information

System Information
Operating System iOS 15.0.1
Model iPhone 12
Model IDiPhone13,2
Motherboard D53gAP
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 3.62 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 614
65.7 IPS
 
Image Classification (F16)
100% 591
63.3 IPS
 
Image Classification (I8)
81% 420
45.0 IPS
 
Image Segmentation (F32)
100% 937
5.79 IPS
 
Image Segmentation (F16)
100% 916
5.66 IPS
 
Image Segmentation (I8)
89% 1379
8.52 IPS
 
Pose Estimation (F32)
100% 346
1.40 IPS
 
Pose Estimation (F16)
100% 347
1.40 IPS
 
Pose Estimation (I8)
80% 426
1.72 IPS
 
Object Detection (F32)
100% 858
30.1 IPS
 
Object Detection (F16)
100% 864
30.3 IPS
 
Object Detection (I8)
52% 721
25.3 IPS
 
Face Detection (F32)
100% 1050
12.1 IPS
 
Face Detection (F16)
100% 1023
11.8 IPS
 
Face Detection (I8)
75% 806
9.26 IPS
 
Text Classification (F32)
100% 2347
928.1 IPS
 
Text Classification (F16)
100% 2383
942.5 IPS
 
Machine Translation (F32)
100% 1691
260.6 IPS
 
Machine Translation (F16)
100% 1680
259.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download