Geekbench ML Score

1017
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 15 2022 01:05 AM
Views 1

System Information

System Information
Operating System iOS 15.2
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% 948
101.6 IPS
 
Image Classification (F16)
100% 942
100.9 IPS
 
Image Classification (I8)
81% 389
41.6 IPS
 
Image Segmentation (F32)
100% 1339
8.27 IPS
 
Image Segmentation (F16)
100% 1342
8.29 IPS
 
Image Segmentation (I8)
89% 1522
9.40 IPS
 
Pose Estimation (F32)
100% 670
2.71 IPS
 
Pose Estimation (F16)
100% 668
2.70 IPS
 
Pose Estimation (I8)
80% 783
3.17 IPS
 
Object Detection (F32)
100% 1432
50.3 IPS
 
Object Detection (F16)
100% 1429
50.1 IPS
 
Object Detection (I8)
52% 668
23.4 IPS
 
Face Detection (F32)
100% 1630
18.7 IPS
 
Face Detection (F16)
100% 1641
18.9 IPS
 
Face Detection (I8)
75% 797
9.16 IPS
 
Text Classification (F32)
100% 679
268.4 IPS
 
Text Classification (F16)
100% 625
247.2 IPS
 
Machine Translation (F32)
100% 1840
283.6 IPS
 
Machine Translation (F16)
100% 1848
284.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download