Geekbench ML Score

877
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 10:10 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
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 GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 600
64.3 IPS
 
Image Classification (F16)
100% 700
75.0 IPS
 
Image Classification (I8)
81% 359
38.5 IPS
 
Image Segmentation (F32)
100% 2034
12.6 IPS
 
Image Segmentation (F16)
100% 3489
21.6 IPS
 
Image Segmentation (I8)
89% 663
4.10 IPS
 
Pose Estimation (F32)
100% 648
2.62 IPS
 
Pose Estimation (F16)
100% 2176
8.81 IPS
 
Pose Estimation (I8)
80% 130
0.53 IPS
 
Object Detection (F32)
100% 1287
45.2 IPS
 
Object Detection (F16)
99% 1335
46.8 IPS
 
Object Detection (I8)
52% 510
17.9 IPS
 
Face Detection (F32)
100% 2117
24.3 IPS
 
Face Detection (F16)
97% 4275
49.1 IPS
 
Face Detection (I8)
75% 485
5.57 IPS
 
Text Classification (F32)
100% 451
178.4 IPS
 
Text Classification (F16)
98% 678
268.3 IPS
 
Machine Translation (F32)
100% 737
113.7 IPS
 
Machine Translation (F16)
100% 738
113.7 IPS
 

Compare

Set Baseline