Geekbench ML Score

679
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 25 2021 05:11 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% 659
70.6 IPS
 
Image Classification (F16)
100% 657
70.4 IPS
 
Image Classification (I8)
81% 170
18.2 IPS
 
Image Segmentation (F32)
100% 944
5.83 IPS
 
Image Segmentation (F16)
100% 938
5.79 IPS
 
Image Segmentation (I8)
89% 1205
7.45 IPS
 
Pose Estimation (F32)
100% 450
1.82 IPS
 
Pose Estimation (F16)
100% 450
1.82 IPS
 
Pose Estimation (I8)
80% 461
1.86 IPS
 
Object Detection (F32)
100% 989
34.7 IPS
 
Object Detection (F16)
100% 984
34.5 IPS
 
Object Detection (I8)
52% 445
15.6 IPS
 
Face Detection (F32)
100% 1175
13.5 IPS
 
Face Detection (F16)
100% 1173
13.5 IPS
 
Face Detection (I8)
75% 716
8.23 IPS
 
Text Classification (F32)
100% 458
181.3 IPS
 
Text Classification (F16)
100% 459
181.6 IPS
 
Machine Translation (F32)
100% 990
152.6 IPS
 
Machine Translation (F16)
100% 984
151.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download