Geekbench ML Score

870
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date June 11 2021 03:01 AM
Views 1

System Information

System Information
Operating System iOS 14.1
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% 632
67.8 IPS
 
Image Classification (F16)
100% 609
65.2 IPS
 
Image Classification (I8)
81% 438
47.0 IPS
 
Image Segmentation (F32)
100% 952
5.88 IPS
 
Image Segmentation (F16)
100% 929
5.74 IPS
 
Image Segmentation (I8)
89% 1372
8.47 IPS
 
Pose Estimation (F32)
100% 349
1.41 IPS
 
Pose Estimation (F16)
100% 343
1.39 IPS
 
Pose Estimation (I8)
80% 423
1.71 IPS
 
Object Detection (F32)
100% 843
29.6 IPS
 
Object Detection (F16)
100% 852
29.9 IPS
 
Object Detection (I8)
52% 736
25.8 IPS
 
Face Detection (F32)
100% 1060
12.2 IPS
 
Face Detection (F16)
100% 1028
11.8 IPS
 
Face Detection (I8)
75% 813
9.35 IPS
 
Text Classification (F32)
100% 2280
901.7 IPS
 
Text Classification (F16)
100% 2280
901.7 IPS
 
Machine Translation (F32)
100% 1682
259.3 IPS
 
Machine Translation (F16)
100% 1686
259.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download