Geekbench ML Score

825
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 09:39 AM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone 8
Model IDiPhone10,4
Motherboard D201AP
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% 596
63.8 IPS
 
Image Classification (F16)
100% 704
75.5 IPS
 
Image Classification (I8)
81% 354
38.0 IPS
 
Image Segmentation (F32)
100% 2024
12.5 IPS
 
Image Segmentation (F16)
100% 3527
21.8 IPS
 
Image Segmentation (I8)
89% 602
3.72 IPS
 
Pose Estimation (F32)
100% 647
2.62 IPS
 
Pose Estimation (F16)
100% 2174
8.80 IPS
 
Pose Estimation (I8)
80% 118
0.48 IPS
 
Object Detection (F32)
100% 1246
43.7 IPS
 
Object Detection (F16)
99% 1202
42.2 IPS
 
Object Detection (I8)
52% 444
15.6 IPS
 
Face Detection (F32)
100% 1923
22.1 IPS
 
Face Detection (F16)
97% 4146
47.6 IPS
 
Face Detection (I8)
75% 392
4.50 IPS
 
Text Classification (F32)
100% 462
182.7 IPS
 
Text Classification (F16)
98% 676
267.3 IPS
 
Machine Translation (F32)
100% 621
95.7 IPS
 
Machine Translation (F16)
100% 615
94.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download