Geekbench ML Score

1007
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

User larryoh
Upload Date May 14 2022 11:33 AM
Views 2

System Information

System Information
Operating System iOS 15.4.1
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,4
Motherboard J517AP
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 7.33 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 935
100.2 IPS
 
Image Classification (F16)
100% 942
100.9 IPS
 
Image Classification (I8)
81% 397
42.6 IPS
 
Image Segmentation (F32)
100% 1329
8.21 IPS
 
Image Segmentation (F16)
100% 1333
8.24 IPS
 
Image Segmentation (I8)
89% 1469
9.08 IPS
 
Pose Estimation (F32)
100% 660
2.67 IPS
 
Pose Estimation (F16)
100% 651
2.63 IPS
 
Pose Estimation (I8)
80% 799
3.23 IPS
 
Object Detection (F32)
100% 1463
51.3 IPS
 
Object Detection (F16)
100% 1460
51.2 IPS
 
Object Detection (I8)
52% 595
20.9 IPS
 
Face Detection (F32)
100% 1664
19.1 IPS
 
Face Detection (F16)
100% 1696
19.5 IPS
 
Face Detection (I8)
75% 816
9.38 IPS
 
Text Classification (F32)
100% 607
239.9 IPS
 
Text Classification (F16)
100% 606
239.7 IPS
 
Machine Translation (F32)
100% 1874
288.9 IPS
 
Machine Translation (F16)
100% 1842
283.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download