Geekbench ML Score

492
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 01:08 PM
Views 1

System Information

System Information
Operating System iOS 16.0.2
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% 459
49.2 IPS
 
Image Classification (F16)
100% 439
47.1 IPS
 
Image Classification (I8)
81% 216
23.1 IPS
 
Image Segmentation (F32)
100% 713
4.41 IPS
 
Image Segmentation (F16)
100% 664
4.10 IPS
 
Image Segmentation (I8)
89% 898
5.55 IPS
 
Pose Estimation (F32)
100% 190
0.77 IPS
 
Pose Estimation (F16)
100% 183
0.74 IPS
 
Pose Estimation (I8)
80% 222
0.90 IPS
 
Object Detection (F32)
100% 615
21.6 IPS
 
Object Detection (F16)
100% 596
20.9 IPS
 
Object Detection (I8)
52% 413
14.5 IPS
 
Face Detection (F32)
100% 703
8.07 IPS
 
Face Detection (F16)
100% 645
7.41 IPS
 
Face Detection (I8)
75% 477
5.48 IPS
 
Text Classification (F32)
100% 564
222.9 IPS
 
Text Classification (F16)
100% 587
232.1 IPS
 
Machine Translation (F32)
100% 963
148.4 IPS
 
Machine Translation (F16)
100% 954
147.0 IPS
 

Compare

Set Baseline