Geekbench ML Score

556
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 03:23 AM
Views 1

System Information

System Information
Operating System iOS 14.0
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 Cache128 KB x 1
L1 Data Cache128 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 3.70 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 464
49.7 IPS
 
Image Classification (F16)
100% 456
48.9 IPS
 
Image Classification (I8)
81% 279
29.8 IPS
 
Image Segmentation (F32)
100% 763
4.71 IPS
 
Image Segmentation (F16)
100% 758
4.68 IPS
 
Image Segmentation (I8)
89% 976
6.03 IPS
 
Pose Estimation (F32)
100% 246
0.99 IPS
 
Pose Estimation (F16)
100% 154
0.62 IPS
 
Pose Estimation (I8)
80% 226
0.91 IPS
 
Object Detection (F32)
100% 661
23.2 IPS
 
Object Detection (F16)
100% 668
23.4 IPS
 
Object Detection (I8)
52% 524
18.4 IPS
 
Face Detection (F32)
100% 759
8.72 IPS
 
Face Detection (F16)
100% 773
8.88 IPS
 
Face Detection (I8)
75% 603
6.93 IPS
 
Text Classification (F32)
100% 787
311.3 IPS
 
Text Classification (F16)
100% 787
311.2 IPS
 
Machine Translation (F32)
100% 995
153.3 IPS
 
Machine Translation (F16)
100% 998
153.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download