Geekbench ML Score

539
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 23 2022 05:53 AM
Views 1

System Information

System Information
Operating System iOS 15.7
Model iPhone 6s Plus
Model IDiPhone8,2
Motherboard N66mAP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.85 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.94 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 496
53.1 IPS
 
Image Classification (F16)
100% 673
72.1 IPS
 
Image Classification (I8)
81% 193
20.6 IPS
 
Image Segmentation (F32)
100% 1163
7.19 IPS
 
Image Segmentation (F16)
100% 1892
11.7 IPS
 
Image Segmentation (I8)
89% 365
2.26 IPS
 
Pose Estimation (F32)
100% 451
1.82 IPS
 
Pose Estimation (F16)
100% 858
3.47 IPS
 
Pose Estimation (I8)
80% 67
0.27 IPS
 
Object Detection (F32)
100% 702
24.6 IPS
 
Object Detection (F16)
100% 955
33.5 IPS
 
Object Detection (I8)
52% 275
9.65 IPS
 
Face Detection (F32)
100% 1120
12.9 IPS
 
Face Detection (F16)
97% 1974
22.7 IPS
 
Face Detection (I8)
75% 270
3.10 IPS
 
Text Classification (F32)
100% 453
179.3 IPS
 
Text Classification (F16)
98% 614
242.9 IPS
 
Machine Translation (F32)
100% 448
69.0 IPS
 
Machine Translation (F16)
100% 437
67.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download