Geekbench ML Score

1345
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 09:37 AM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone SE (2nd generation)
Model IDiPhone12,8
Motherboard D79AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 2.89 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1260
135.0 IPS
 
Image Classification (F16)
100% 1588
170.2 IPS
 
Image Classification (I8)
81% 416
44.6 IPS
 
Image Segmentation (F32)
100% 3479
21.5 IPS
 
Image Segmentation (F16)
100% 5392
33.3 IPS
 
Image Segmentation (I8)
89% 774
4.78 IPS
 
Pose Estimation (F32)
100% 1427
5.77 IPS
 
Pose Estimation (F16)
100% 4404
17.8 IPS
 
Pose Estimation (I8)
80% 135
0.55 IPS
 
Object Detection (F32)
100% 1485
52.1 IPS
 
Object Detection (F16)
99% 1865
65.5 IPS
 
Object Detection (I8)
52% 615
21.6 IPS
 
Face Detection (F32)
100% 3627
41.7 IPS
 
Face Detection (F16)
97% 5362
61.6 IPS
 
Face Detection (I8)
75% 526
6.05 IPS
 
Text Classification (F32)
100% 974
385.3 IPS
 
Text Classification (F16)
98% 1223
483.8 IPS
 
Machine Translation (F32)
100% 1177
181.5 IPS
 
Machine Translation (F16)
100% 1128
173.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download