Geekbench ML Score

959
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 08:42 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,8
Motherboard J522AP
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 7.31 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 963
103.2 IPS
 
Image Classification (F16)
100% 962
103.1 IPS
 
Image Classification (I8)
81% 273
29.3 IPS
 
Image Segmentation (F32)
100% 1368
8.45 IPS
 
Image Segmentation (F16)
100% 1370
8.46 IPS
 
Image Segmentation (I8)
89% 1417
8.75 IPS
 
Pose Estimation (F32)
100% 633
2.56 IPS
 
Pose Estimation (F16)
100% 609
2.46 IPS
 
Pose Estimation (I8)
80% 760
3.07 IPS
 
Object Detection (F32)
100% 1528
53.6 IPS
 
Object Detection (F16)
100% 1534
53.8 IPS
 
Object Detection (I8)
52% 411
14.4 IPS
 
Face Detection (F32)
100% 1775
20.4 IPS
 
Face Detection (F16)
100% 1783
20.5 IPS
 
Face Detection (I8)
75% 694
7.98 IPS
 
Text Classification (F32)
100% 554
219.2 IPS
 
Text Classification (F16)
100% 561
221.8 IPS
 
Machine Translation (F32)
100% 1885
290.6 IPS
 
Machine Translation (F16)
100% 1883
290.1 IPS
 

Compare

Set Baseline