Geekbench ML Score

1618
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 14 2022 11:33 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 GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1580
169.3 IPS
 
Image Classification (F16)
100% 1612
172.7 IPS
 
Image Classification (I8)
81% 642
68.8 IPS
 
Image Segmentation (F32)
100% 4143
25.6 IPS
 
Image Segmentation (F16)
100% 6049
37.4 IPS
 
Image Segmentation (I8)
89% 1157
7.15 IPS
 
Pose Estimation (F32)
100% 1492
6.04 IPS
 
Pose Estimation (F16)
100% 4976
20.1 IPS
 
Pose Estimation (I8)
80% 211
0.85 IPS
 
Object Detection (F32)
100% 1616
56.7 IPS
 
Object Detection (F16)
99% 1687
59.2 IPS
 
Object Detection (I8)
52% 914
32.1 IPS
 
Face Detection (F32)
100% 4287
49.3 IPS
 
Face Detection (F16)
97% 5376
61.8 IPS
 
Face Detection (I8)
75% 846
9.72 IPS
 
Text Classification (F32)
100% 851
336.4 IPS
 
Text Classification (F16)
98% 1090
431.0 IPS
 
Machine Translation (F32)
100% 1675
258.1 IPS
 
Machine Translation (F16)
100% 1671
257.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download