Geekbench ML Score

877
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 04:43 PM
Views 1

System Information

System Information
Operating System iOS 15.2
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% 627
67.2 IPS
 
Image Classification (F16)
100% 612
65.5 IPS
 
Image Classification (I8)
81% 398
42.7 IPS
 
Image Segmentation (F32)
100% 996
6.15 IPS
 
Image Segmentation (F16)
100% 963
5.95 IPS
 
Image Segmentation (I8)
89% 1345
8.31 IPS
 
Pose Estimation (F32)
100% 362
1.47 IPS
 
Pose Estimation (F16)
100% 354
1.43 IPS
 
Pose Estimation (I8)
80% 435
1.76 IPS
 
Object Detection (F32)
100% 916
32.2 IPS
 
Object Detection (F16)
100% 936
32.8 IPS
 
Object Detection (I8)
52% 675
23.7 IPS
 
Face Detection (F32)
100% 1108
12.7 IPS
 
Face Detection (F16)
100% 1084
12.5 IPS
 
Face Detection (I8)
75% 812
9.33 IPS
 
Text Classification (F32)
100% 2198
869.3 IPS
 
Text Classification (F16)
100% 2190
866.0 IPS
 
Machine Translation (F32)
100% 1679
258.7 IPS
 
Machine Translation (F16)
100% 1671
257.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download