Geekbench ML Score

314
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 15 2021 10:02 AM
Views 1

System Information

System Information
Operating System iOS 14.7.1
Model iPhone 8 Plus
Model IDiPhone10,5
Motherboard D211AP
CPU Information
Name Apple A11 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.39 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 2.90 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 234
25.0 IPS
 
Image Classification (F16)
100% 233
25.0 IPS
 
Image Classification (I8)
81% 302
32.4 IPS
 
Image Segmentation (F32)
100% 385
2.38 IPS
 
Image Segmentation (F16)
100% 387
2.39 IPS
 
Image Segmentation (I8)
89% 656
4.05 IPS
 
Pose Estimation (F32)
100% 86
0.35 IPS
 
Pose Estimation (F16)
100% 87
0.35 IPS
 
Pose Estimation (I8)
80% 119
0.48 IPS
 
Object Detection (F32)
100% 346
12.2 IPS
 
Object Detection (F16)
100% 340
11.9 IPS
 
Object Detection (I8)
52% 470
16.5 IPS
 
Face Detection (F32)
100% 432
4.96 IPS
 
Face Detection (F16)
100% 432
4.97 IPS
 
Face Detection (I8)
75% 447
5.13 IPS
 
Text Classification (F32)
100% 434
171.7 IPS
 
Text Classification (F16)
100% 435
172.2 IPS
 
Machine Translation (F32)
100% 486
75.0 IPS
 
Machine Translation (F16)
100% 484
74.6 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download