Geekbench ML Score

565
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 03:26 PM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPad (8th generation)
Model IDiPad11,6
Motherboard J171aAP
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 2.88 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 453
48.5 IPS
 
Image Classification (F16)
100% 457
48.9 IPS
 
Image Classification (I8)
81% 282
30.3 IPS
 
Image Segmentation (F32)
100% 744
4.60 IPS
 
Image Segmentation (F16)
100% 730
4.51 IPS
 
Image Segmentation (I8)
89% 942
5.82 IPS
 
Pose Estimation (F32)
100% 226
0.91 IPS
 
Pose Estimation (F16)
100% 225
0.91 IPS
 
Pose Estimation (I8)
80% 254
1.03 IPS
 
Object Detection (F32)
100% 656
23.0 IPS
 
Object Detection (F16)
100% 661
23.2 IPS
 
Object Detection (I8)
52% 540
19.0 IPS
 
Face Detection (F32)
100% 826
9.49 IPS
 
Face Detection (F16)
100% 812
9.33 IPS
 
Face Detection (I8)
75% 593
6.81 IPS
 
Text Classification (F32)
100% 777
307.2 IPS
 
Text Classification (F16)
100% 751
297.2 IPS
 
Machine Translation (F32)
100% 971
149.6 IPS
 
Machine Translation (F16)
100% 975
150.2 IPS
 

Compare

Set Baseline