Geekbench ML Score

573
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 22 2021 09:12 PM
Views 1

System Information

System Information
Operating System iOS 14.7.1
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 Cache128 KB x 1
L1 Data Cache128 KB x 1
L2 Cache8.00 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% 484
51.9 IPS
 
Image Classification (F16)
100% 470
50.3 IPS
 
Image Classification (I8)
81% 279
29.9 IPS
 
Image Segmentation (F32)
100% 760
4.69 IPS
 
Image Segmentation (F16)
100% 741
4.58 IPS
 
Image Segmentation (I8)
89% 956
5.90 IPS
 
Pose Estimation (F32)
100% 232
0.94 IPS
 
Pose Estimation (F16)
100% 227
0.92 IPS
 
Pose Estimation (I8)
80% 231
0.93 IPS
 
Object Detection (F32)
100% 681
23.9 IPS
 
Object Detection (F16)
100% 681
23.9 IPS
 
Object Detection (I8)
52% 545
19.1 IPS
 
Face Detection (F32)
100% 808
9.28 IPS
 
Face Detection (F16)
100% 809
9.29 IPS
 
Face Detection (I8)
75% 610
7.01 IPS
 
Text Classification (F32)
100% 779
308.1 IPS
 
Text Classification (F16)
100% 792
313.4 IPS
 
Machine Translation (F32)
100% 997
153.6 IPS
 
Machine Translation (F16)
100% 996
153.6 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download