Geekbench ML Score

302
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 23 2022 05:57 AM
Views 1

System Information

System Information
Operating System iOS 15.7
Model iPhone 6s
Model IDiPhone8,1
Motherboard N71AP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.85 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.96 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 206
22.0 IPS
 
Image Classification (F16)
100% 201
21.5 IPS
 
Image Classification (I8)
81% 333
35.7 IPS
 
Image Segmentation (F32)
100% 375
2.31 IPS
 
Image Segmentation (F16)
100% 389
2.40 IPS
 
Image Segmentation (I8)
89% 587
3.63 IPS
 
Pose Estimation (F32)
100% 114
0.46 IPS
 
Pose Estimation (F16)
100% 115
0.47 IPS
 
Pose Estimation (I8)
80% 105
0.42 IPS
 
Object Detection (F32)
100% 312
10.9 IPS
 
Object Detection (F16)
100% 330
11.6 IPS
 
Object Detection (I8)
52% 433
15.2 IPS
 
Face Detection (F32)
100% 398
4.57 IPS
 
Face Detection (F16)
100% 384
4.41 IPS
 
Face Detection (I8)
75% 410
4.71 IPS
 
Text Classification (F32)
100% 409
161.9 IPS
 
Text Classification (F16)
100% 416
164.4 IPS
 
Machine Translation (F32)
100% 404
62.2 IPS
 
Machine Translation (F16)
100% 431
66.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download