Geekbench ML Score

586
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 24 2021 01:00 AM
Views 1

System Information

System Information
Operating System iOS 14.8
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 Cache128 KB x 1
L1 Data Cache128 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 3.70 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 466
49.9 IPS
 
Image Classification (F16)
100% 465
49.9 IPS
 
Image Classification (I8)
81% 273
29.2 IPS
 
Image Segmentation (F32)
100% 785
4.85 IPS
 
Image Segmentation (F16)
100% 782
4.83 IPS
 
Image Segmentation (I8)
89% 982
6.07 IPS
 
Pose Estimation (F32)
100% 255
1.03 IPS
 
Pose Estimation (F16)
100% 242
0.98 IPS
 
Pose Estimation (I8)
80% 284
1.15 IPS
 
Object Detection (F32)
100% 705
24.8 IPS
 
Object Detection (F16)
100% 643
22.6 IPS
 
Object Detection (I8)
52% 534
18.7 IPS
 
Face Detection (F32)
100% 834
9.59 IPS
 
Face Detection (F16)
100% 830
9.53 IPS
 
Face Detection (I8)
75% 631
7.25 IPS
 
Text Classification (F32)
100% 789
312.1 IPS
 
Text Classification (F16)
100% 775
306.6 IPS
 
Machine Translation (F32)
100% 995
153.4 IPS
 
Machine Translation (F16)
100% 996
153.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download