Geekbench ML Score

711
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 05:44 AM
Views 1

System Information

System Information
Operating System iOS 16.1.1
Model iPhone 8 Plus
Model IDiPhone10,5
Motherboard D211AP
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 2.90 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 633
67.8 IPS
 
Image Classification (F16)
100% 695
74.5 IPS
 
Image Classification (I8)
81% 202
21.6 IPS
 
Image Segmentation (F32)
100% 2007
12.4 IPS
 
Image Segmentation (F16)
100% 3486
21.5 IPS
 
Image Segmentation (I8)
89% 371
2.29 IPS
 
Pose Estimation (F32)
100% 649
2.62 IPS
 
Pose Estimation (F16)
100% 2171
8.78 IPS
 
Pose Estimation (I8)
80% 75
0.30 IPS
 
Object Detection (F32)
100% 1170
41.1 IPS
 
Object Detection (F16)
99% 1120
39.3 IPS
 
Object Detection (I8)
52% 290
10.2 IPS
 
Face Detection (F32)
100% 2064
23.7 IPS
 
Face Detection (F16)
97% 4120
47.3 IPS
 
Face Detection (I8)
75% 278
3.20 IPS
 
Text Classification (F32)
100% 452
178.7 IPS
 
Text Classification (F16)
98% 669
264.7 IPS
 
Machine Translation (F32)
100% 484
74.6 IPS
 
Machine Translation (F16)
100% 480
73.9 IPS
 

Compare

Set Baseline