Geekbench ML Score

2631
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 06:47 PM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,11
Motherboard J523xAP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 15.34 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4119
441.3 IPS
 
Image Classification (F16)
100% 5742
615.2 IPS
 
Image Classification (I8)
81% 674
72.3 IPS
 
Image Segmentation (F32)
100% 7797
48.2 IPS
 
Image Segmentation (F16)
100% 11283
69.7 IPS
 
Image Segmentation (I8)
89% 1212
7.49 IPS
 
Pose Estimation (F32)
100% 2806
11.4 IPS
 
Pose Estimation (F16)
100% 6685
27.0 IPS
 
Pose Estimation (I8)
80% 213
0.86 IPS
 
Object Detection (F32)
100% 3738
131.2 IPS
 
Object Detection (F16)
100% 3796
133.2 IPS
 
Object Detection (I8)
52% 725
25.4 IPS
 
Face Detection (F32)
100% 6792
78.0 IPS
 
Face Detection (F16)
97% 12111
139.1 IPS
 
Face Detection (I8)
75% 672
7.72 IPS
 
Text Classification (F32)
100% 3042
1.20 KIPS
 
Text Classification (F16)
100% 3270
1.29 KIPS
 
Machine Translation (F32)
100% 1513
233.1 IPS
 
Machine Translation (F16)
100% 1657
255.4 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download