Geekbench ML Score

1118
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 01:01 PM
Views 1

System Information

System Information
Operating System iOS 16.0.2
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 731
78.4 IPS
 
Image Classification (F16)
100% 1079
115.6 IPS
 
Image Classification (I8)
81% 405
43.4 IPS
 
Image Segmentation (F32)
100% 2986
18.4 IPS
 
Image Segmentation (F16)
100% 4429
27.4 IPS
 
Image Segmentation (I8)
89% 735
4.54 IPS
 
Pose Estimation (F32)
100% 1197
4.84 IPS
 
Pose Estimation (F16)
100% 3405
13.8 IPS
 
Pose Estimation (I8)
80% 139
0.56 IPS
 
Object Detection (F32)
100% 1410
49.5 IPS
 
Object Detection (F16)
99% 1488
52.2 IPS
 
Object Detection (I8)
52% 547
19.2 IPS
 
Face Detection (F32)
100% 3094
35.5 IPS
 
Face Detection (F16)
97% 5107
58.7 IPS
 
Face Detection (I8)
75% 481
5.53 IPS
 
Text Classification (F32)
100% 673
266.0 IPS
 
Text Classification (F16)
98% 828
327.5 IPS
 
Machine Translation (F32)
100% 996
153.4 IPS
 
Machine Translation (F16)
100% 987
152.0 IPS
 

Compare

Set Baseline