Geekbench ML Score

421
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 21 2021 07:28 PM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 323
34.7 IPS
 
Image Classification (F16)
100% 323
34.7 IPS
 
Image Classification (I8)
81% 266
28.5 IPS
 
Image Segmentation (F32)
100% 548
3.38 IPS
 
Image Segmentation (F16)
100% 548
3.39 IPS
 
Image Segmentation (I8)
89% 770
4.76 IPS
 
Pose Estimation (F32)
100% 147
0.60 IPS
 
Pose Estimation (F16)
100% 147
0.59 IPS
 
Pose Estimation (I8)
80% 192
0.78 IPS
 
Object Detection (F32)
100% 479
16.8 IPS
 
Object Detection (F16)
100% 518
18.2 IPS
 
Object Detection (I8)
52% 472
16.6 IPS
 
Face Detection (F32)
100% 594
6.82 IPS
 
Face Detection (F16)
100% 595
6.84 IPS
 
Face Detection (I8)
75% 504
5.79 IPS
 
Text Classification (F32)
100% 537
212.5 IPS
 
Text Classification (F16)
100% 540
213.6 IPS
 
Machine Translation (F32)
100% 673
103.7 IPS
 
Machine Translation (F16)
100% 671
103.4 IPS
 

Compare

Set Baseline Geekbench 6 now available