Geekbench ML Score

466
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 15 2022 02:15 AM
Views 1

System Information

System Information
Operating System iOS 15.2
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% 369
39.5 IPS
 
Image Classification (F16)
100% 368
39.4 IPS
 
Image Classification (I8)
81% 281
30.1 IPS
 
Image Segmentation (F32)
100% 596
3.68 IPS
 
Image Segmentation (F16)
100% 591
3.65 IPS
 
Image Segmentation (I8)
89% 846
5.23 IPS
 
Pose Estimation (F32)
100% 187
0.76 IPS
 
Pose Estimation (F16)
100% 177
0.72 IPS
 
Pose Estimation (I8)
80% 191
0.77 IPS
 
Object Detection (F32)
100% 521
18.3 IPS
 
Object Detection (F16)
100% 522
18.3 IPS
 
Object Detection (I8)
52% 480
16.8 IPS
 
Face Detection (F32)
100% 660
7.58 IPS
 
Face Detection (F16)
100% 651
7.48 IPS
 
Face Detection (I8)
75% 553
6.35 IPS
 
Text Classification (F32)
100% 618
244.5 IPS
 
Text Classification (F16)
100% 694
274.5 IPS
 
Machine Translation (F32)
100% 737
113.6 IPS
 
Machine Translation (F16)
100% 737
113.6 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download