Geekbench ML Score

690
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 05:14 PM
Views 1

System Information

System Information
Operating System iOS 15.1
Model iPad Pro (11-inch)
Model IDiPad8,3
Motherboard J318AP
CPU Information
Name Apple A12X Bionic
Topology 1 Processor, 8 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 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 643
68.9 IPS
 
Image Classification (F16)
100% 643
68.9 IPS
 
Image Classification (I8)
81% 242
25.9 IPS
 
Image Segmentation (F32)
100% 947
5.85 IPS
 
Image Segmentation (F16)
100% 933
5.76 IPS
 
Image Segmentation (I8)
89% 1210
7.48 IPS
 
Pose Estimation (F32)
100% 450
1.82 IPS
 
Pose Estimation (F16)
100% 451
1.83 IPS
 
Pose Estimation (I8)
80% 464
1.88 IPS
 
Object Detection (F32)
100% 988
34.7 IPS
 
Object Detection (F16)
100% 984
34.5 IPS
 
Object Detection (I8)
52% 435
15.3 IPS
 
Face Detection (F32)
100% 1170
13.4 IPS
 
Face Detection (F16)
100% 1174
13.5 IPS
 
Face Detection (I8)
75% 697
8.01 IPS
 
Text Classification (F32)
100% 463
183.3 IPS
 
Text Classification (F16)
100% 477
188.8 IPS
 
Machine Translation (F32)
100% 986
151.9 IPS
 
Machine Translation (F16)
100% 984
151.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download