Geekbench ML Score

543
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 12:32 PM
Views 1

System Information

System Information
Operating System iOS 16.1.1
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% 433
46.3 IPS
 
Image Classification (F16)
100% 426
45.6 IPS
 
Image Classification (I8)
81% 271
29.0 IPS
 
Image Segmentation (F32)
100% 688
4.25 IPS
 
Image Segmentation (F16)
100% 681
4.21 IPS
 
Image Segmentation (I8)
89% 940
5.80 IPS
 
Pose Estimation (F32)
100% 196
0.79 IPS
 
Pose Estimation (F16)
100% 219
0.89 IPS
 
Pose Estimation (I8)
80% 259
1.05 IPS
 
Object Detection (F32)
100% 627
22.0 IPS
 
Object Detection (F16)
100% 660
23.2 IPS
 
Object Detection (I8)
52% 484
17.0 IPS
 
Face Detection (F32)
100% 804
9.24 IPS
 
Face Detection (F16)
100% 794
9.12 IPS
 
Face Detection (I8)
75% 562
6.46 IPS
 
Text Classification (F32)
100% 761
300.8 IPS
 
Text Classification (F16)
100% 764
302.0 IPS
 
Machine Translation (F32)
100% 933
143.7 IPS
 
Machine Translation (F16)
100% 974
150.2 IPS
 

Compare

Set Baseline