Geekbench ML Score

313
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 17 2021 12:43 PM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPhone SE
Model IDiPhone8,4
Motherboard N69uAP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.80 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.97 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 210
22.5 IPS
 
Image Classification (F16)
100% 200
21.4 IPS
 
Image Classification (I8)
81% 344
36.9 IPS
 
Image Segmentation (F32)
100% 392
2.42 IPS
 
Image Segmentation (F16)
100% 369
2.28 IPS
 
Image Segmentation (I8)
89% 606
3.74 IPS
 
Pose Estimation (F32)
100% 116
0.47 IPS
 
Pose Estimation (F16)
100% 115
0.47 IPS
 
Pose Estimation (I8)
80% 117
0.47 IPS
 
Object Detection (F32)
100% 314
11.0 IPS
 
Object Detection (F16)
100% 349
12.3 IPS
 
Object Detection (I8)
52% 464
16.3 IPS
 
Face Detection (F32)
100% 412
4.74 IPS
 
Face Detection (F16)
100% 401
4.61 IPS
 
Face Detection (I8)
75% 443
5.09 IPS
 
Text Classification (F32)
100% 434
171.8 IPS
 
Text Classification (F16)
100% 427
168.7 IPS
 
Machine Translation (F32)
100% 440
67.8 IPS
 
Machine Translation (F16)
100% 451
69.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download