Geekbench ML Score

1006
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 15 2022 02:01 AM
Views 1

System Information

System Information
Operating System iOS 15.1
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% 944
101.1 IPS
 
Image Classification (F16)
100% 945
101.2 IPS
 
Image Classification (I8)
81% 389
41.6 IPS
 
Image Segmentation (F32)
100% 1342
8.29 IPS
 
Image Segmentation (F16)
100% 1331
8.22 IPS
 
Image Segmentation (I8)
89% 1475
9.11 IPS
 
Pose Estimation (F32)
100% 666
2.69 IPS
 
Pose Estimation (F16)
100% 642
2.60 IPS
 
Pose Estimation (I8)
80% 796
3.22 IPS
 
Object Detection (F32)
100% 1467
51.5 IPS
 
Object Detection (F16)
100% 1451
50.9 IPS
 
Object Detection (I8)
52% 593
20.8 IPS
 
Face Detection (F32)
100% 1622
18.6 IPS
 
Face Detection (F16)
100% 1621
18.6 IPS
 
Face Detection (I8)
75% 805
9.24 IPS
 
Text Classification (F32)
100% 624
246.6 IPS
 
Text Classification (F16)
100% 616
243.8 IPS
 
Machine Translation (F32)
100% 1877
289.2 IPS
 
Machine Translation (F16)
100% 1874
288.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download