Geekbench ML Score

571
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 06:44 AM
Views 1

System Information

System Information
Operating System iOS 15.0.2
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% 462
49.5 IPS
 
Image Classification (F16)
100% 455
48.8 IPS
 
Image Classification (I8)
81% 271
29.0 IPS
 
Image Segmentation (F32)
100% 759
4.69 IPS
 
Image Segmentation (F16)
100% 760
4.70 IPS
 
Image Segmentation (I8)
89% 968
5.98 IPS
 
Pose Estimation (F32)
100% 247
1.00 IPS
 
Pose Estimation (F16)
100% 246
1.00 IPS
 
Pose Estimation (I8)
80% 251
1.01 IPS
 
Object Detection (F32)
100% 671
23.6 IPS
 
Object Detection (F16)
100% 672
23.6 IPS
 
Object Detection (I8)
52% 487
17.1 IPS
 
Face Detection (F32)
100% 812
9.33 IPS
 
Face Detection (F16)
100% 807
9.27 IPS
 
Face Detection (I8)
75% 584
6.71 IPS
 
Text Classification (F32)
100% 776
306.9 IPS
 
Text Classification (F16)
100% 772
305.5 IPS
 
Machine Translation (F32)
100% 990
152.6 IPS
 
Machine Translation (F16)
100% 988
152.3 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download