Geekbench ML Score

375
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 22 2021 08:42 PM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone 8
Model IDiPhone10,1
Motherboard D20AP
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 1.93 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 380
40.7 IPS
 
Image Classification (F16)
100% 361
38.7 IPS
 
Image Classification (I8)
81% 291
31.1 IPS
 
Image Segmentation (F32)
100% 427
2.64 IPS
 
Image Segmentation (F16)
100% 227
1.40 IPS
 
Image Segmentation (I8)
89% 689
4.26 IPS
 
Pose Estimation (F32)
100% 132
0.53 IPS
 
Pose Estimation (F16)
100% 107
0.43 IPS
 
Pose Estimation (I8)
80% 129
0.52 IPS
 
Object Detection (F32)
100% 337
11.8 IPS
 
Object Detection (F16)
100% 413
14.5 IPS
 
Object Detection (I8)
52% 486
17.1 IPS
 
Face Detection (F32)
100% 548
6.30 IPS
 
Face Detection (F16)
100% 550
6.32 IPS
 
Face Detection (I8)
75% 557
6.40 IPS
 
Text Classification (F32)
100% 507
200.7 IPS
 
Text Classification (F16)
100% 579
229.1 IPS
 
Machine Translation (F32)
100% 697
107.4 IPS
 
Machine Translation (F16)
100% 734
113.1 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download