Geekbench ML Score

664
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 10:06 AM
Views 1

System Information

System Information
Operating System iOS 14.7.1
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% 613
65.6 IPS
 
Image Classification (F16)
100% 573
61.4 IPS
 
Image Classification (I8)
81% 225
24.1 IPS
 
Image Segmentation (F32)
100% 889
5.49 IPS
 
Image Segmentation (F16)
100% 837
5.17 IPS
 
Image Segmentation (I8)
89% 1238
7.65 IPS
 
Pose Estimation (F32)
100% 288
1.16 IPS
 
Pose Estimation (F16)
100% 277
1.12 IPS
 
Pose Estimation (I8)
80% 368
1.49 IPS
 
Object Detection (F32)
100% 838
29.4 IPS
 
Object Detection (F16)
100% 843
29.6 IPS
 
Object Detection (I8)
52% 428
15.0 IPS
 
Face Detection (F32)
100% 988
11.3 IPS
 
Face Detection (F16)
100% 934
10.7 IPS
 
Face Detection (I8)
75% 693
7.97 IPS
 
Text Classification (F32)
100% 568
224.5 IPS
 
Text Classification (F16)
100% 610
241.1 IPS
 
Machine Translation (F32)
100% 1729
266.4 IPS
 
Machine Translation (F16)
100% 1726
266.0 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download