Geekbench ML Score

722
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 04:54 AM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPad (6th generation)
Model IDiPad7,5
Motherboard J71bAP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.32 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.93 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 570
61.1 IPS
 
Image Classification (F16)
100% 583
62.4 IPS
 
Image Classification (I8)
81% 318
34.1 IPS
 
Image Segmentation (F32)
100% 1535
9.48 IPS
 
Image Segmentation (F16)
100% 2574
15.9 IPS
 
Image Segmentation (I8)
89% 588
3.63 IPS
 
Pose Estimation (F32)
100% 643
2.60 IPS
 
Pose Estimation (F16)
100% 1214
4.91 IPS
 
Pose Estimation (I8)
80% 124
0.50 IPS
 
Object Detection (F32)
100% 952
33.4 IPS
 
Object Detection (F16)
100% 1179
41.4 IPS
 
Object Detection (I8)
52% 457
16.0 IPS
 
Face Detection (F32)
100% 1489
17.1 IPS
 
Face Detection (F16)
97% 2704
31.1 IPS
 
Face Detection (I8)
75% 417
4.79 IPS
 
Text Classification (F32)
100% 427
169.0 IPS
 
Text Classification (F16)
98% 520
205.8 IPS
 
Machine Translation (F32)
100% 672
103.6 IPS
 
Machine Translation (F16)
100% 676
104.2 IPS
 

Compare

Set Baseline