Geekbench ML Score

936
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 07 2022 02:01 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 GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 634
67.9 IPS
 
Image Classification (F16)
100% 1039
111.3 IPS
 
Image Classification (I8)
81% 273
29.3 IPS
 
Image Segmentation (F32)
100% 2913
18.0 IPS
 
Image Segmentation (F16)
100% 4714
29.1 IPS
 
Image Segmentation (I8)
89% 510
3.15 IPS
 
Pose Estimation (F32)
100% 1100
4.45 IPS
 
Pose Estimation (F16)
100% 2997
12.1 IPS
 
Pose Estimation (I8)
80% 97
0.39 IPS
 
Object Detection (F32)
100% 1104
38.7 IPS
 
Object Detection (F16)
99% 1373
48.2 IPS
 
Object Detection (I8)
52% 380
13.3 IPS
 
Face Detection (F32)
100% 2880
33.1 IPS
 
Face Detection (F16)
97% 4722
54.3 IPS
 
Face Detection (I8)
75% 377
4.33 IPS
 
Text Classification (F32)
100% 663
262.1 IPS
 
Text Classification (F16)
98% 797
315.3 IPS
 
Machine Translation (F32)
100% 664
102.4 IPS
 
Machine Translation (F16)
100% 684
105.4 IPS
 

Compare

Set Baseline Geekbench 6 now available