Geekbench ML Score

408
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 24 2021 01:36 AM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone XR
Model IDiPhone11,8
Motherboard N841AP
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 2.77 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 315
33.7 IPS
 
Image Classification (F16)
100% 314
33.7 IPS
 
Image Classification (I8)
81% 265
28.4 IPS
 
Image Segmentation (F32)
100% 526
3.25 IPS
 
Image Segmentation (F16)
100% 524
3.24 IPS
 
Image Segmentation (I8)
89% 744
4.60 IPS
 
Pose Estimation (F32)
100% 140
0.57 IPS
 
Pose Estimation (F16)
100% 140
0.57 IPS
 
Pose Estimation (I8)
80% 190
0.77 IPS
 
Object Detection (F32)
100% 463
16.3 IPS
 
Object Detection (F16)
100% 463
16.2 IPS
 
Object Detection (I8)
52% 471
16.5 IPS
 
Face Detection (F32)
100% 575
6.60 IPS
 
Face Detection (F16)
100% 580
6.66 IPS
 
Face Detection (I8)
75% 503
5.78 IPS
 
Text Classification (F32)
100% 513
203.0 IPS
 
Text Classification (F16)
100% 516
204.0 IPS
 
Machine Translation (F32)
100% 668
102.9 IPS
 
Machine Translation (F16)
100% 670
103.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download