Geekbench ML Score

410
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 07 2022 01:58 AM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPhone XR
Model IDiPhone11,8
Motherboard N841AP
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 2.77 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 320
34.3 IPS
 
Image Classification (F16)
100% 319
34.2 IPS
 
Image Classification (I8)
81% 271
29.1 IPS
 
Image Segmentation (F32)
100% 519
3.21 IPS
 
Image Segmentation (F16)
100% 520
3.21 IPS
 
Image Segmentation (I8)
89% 741
4.58 IPS
 
Pose Estimation (F32)
100% 141
0.57 IPS
 
Pose Estimation (F16)
100% 140
0.57 IPS
 
Pose Estimation (I8)
80% 192
0.78 IPS
 
Object Detection (F32)
100% 462
16.2 IPS
 
Object Detection (F16)
100% 466
16.4 IPS
 
Object Detection (I8)
52% 471
16.5 IPS
 
Face Detection (F32)
100% 590
6.77 IPS
 
Face Detection (F16)
100% 590
6.78 IPS
 
Face Detection (I8)
75% 508
5.83 IPS
 
Text Classification (F32)
100% 528
208.9 IPS
 
Text Classification (F16)
100% 528
208.9 IPS
 
Machine Translation (F32)
100% 660
101.7 IPS
 
Machine Translation (F16)
100% 656
101.1 IPS
 

Compare

Set Baseline Geekbench 6 now available