Geekbench ML Score

692
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 17 2021 12:35 PM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPad Pro (11-inch)
Model IDiPad8,2
Motherboard J317xAP
CPU Information
Name Apple A12X Bionic
Topology 1 Processor, 8 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 5.57 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 645
69.1 IPS
 
Image Classification (F16)
100% 646
69.2 IPS
 
Image Classification (I8)
81% 246
26.3 IPS
 
Image Segmentation (F32)
100% 929
5.74 IPS
 
Image Segmentation (F16)
100% 931
5.75 IPS
 
Image Segmentation (I8)
89% 1201
7.42 IPS
 
Pose Estimation (F32)
100% 452
1.83 IPS
 
Pose Estimation (F16)
100% 452
1.83 IPS
 
Pose Estimation (I8)
80% 464
1.88 IPS
 
Object Detection (F32)
100% 993
34.8 IPS
 
Object Detection (F16)
100% 996
34.9 IPS
 
Object Detection (I8)
52% 442
15.5 IPS
 
Face Detection (F32)
100% 1174
13.5 IPS
 
Face Detection (F16)
100% 1176
13.5 IPS
 
Face Detection (I8)
75% 723
8.30 IPS
 
Text Classification (F32)
100% 460
182.1 IPS
 
Text Classification (F16)
100% 470
186.0 IPS
 
Machine Translation (F32)
100% 989
152.4 IPS
 
Machine Translation (F16)
100% 988
152.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download