Geekbench ML Score

571
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 15.2.1
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 3.69 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 475
50.9 IPS
 
Image Classification (F16)
100% 467
50.1 IPS
 
Image Classification (I8)
81% 283
30.3 IPS
 
Image Segmentation (F32)
100% 751
4.64 IPS
 
Image Segmentation (F16)
100% 746
4.61 IPS
 
Image Segmentation (I8)
89% 946
5.84 IPS
 
Pose Estimation (F32)
100% 225
0.91 IPS
 
Pose Estimation (F16)
100% 228
0.92 IPS
 
Pose Estimation (I8)
80% 264
1.07 IPS
 
Object Detection (F32)
100% 664
23.3 IPS
 
Object Detection (F16)
100% 661
23.2 IPS
 
Object Detection (I8)
52% 542
19.0 IPS
 
Face Detection (F32)
100% 841
9.66 IPS
 
Face Detection (F16)
100% 798
9.16 IPS
 
Face Detection (I8)
75% 609
7.00 IPS
 
Text Classification (F32)
100% 764
302.2 IPS
 
Text Classification (F16)
100% 763
301.8 IPS
 
Machine Translation (F32)
100% 980
151.1 IPS
 
Machine Translation (F16)
100% 978
150.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download