Geekbench ML Score

858
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 08:49 AM
Views 1

System Information

System Information
Operating System iOS 15.6.1
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% 601
64.4 IPS
 
Image Classification (F16)
100% 702
75.2 IPS
 
Image Classification (I8)
81% 360
38.6 IPS
 
Image Segmentation (F32)
100% 1995
12.3 IPS
 
Image Segmentation (F16)
100% 3552
21.9 IPS
 
Image Segmentation (I8)
89% 662
4.09 IPS
 
Pose Estimation (F32)
100% 648
2.62 IPS
 
Pose Estimation (F16)
100% 2176
8.80 IPS
 
Pose Estimation (I8)
80% 125
0.51 IPS
 
Object Detection (F32)
100% 1300
45.6 IPS
 
Object Detection (F16)
99% 1273
44.7 IPS
 
Object Detection (I8)
52% 443
15.5 IPS
 
Face Detection (F32)
100% 2059
23.7 IPS
 
Face Detection (F16)
97% 4241
48.7 IPS
 
Face Detection (I8)
75% 427
4.91 IPS
 
Text Classification (F32)
100% 464
183.3 IPS
 
Text Classification (F16)
98% 676
267.2 IPS
 
Machine Translation (F32)
100% 699
107.7 IPS
 
Machine Translation (F16)
100% 739
113.9 IPS
 

Compare

Set Baseline