Geekbench ML Score

1115
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 14 2021 07:03 AM
Views 1

System Information

System Information
Operating System iOS 15.0.1
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% 639
68.4 IPS
 
Image Classification (F16)
100% 1041
111.6 IPS
 
Image Classification (I8)
81% 401
42.9 IPS
 
Image Segmentation (F32)
100% 3086
19.1 IPS
 
Image Segmentation (F16)
100% 4804
29.7 IPS
 
Image Segmentation (I8)
89% 736
4.54 IPS
 
Pose Estimation (F32)
100% 1209
4.89 IPS
 
Pose Estimation (F16)
100% 3448
14.0 IPS
 
Pose Estimation (I8)
80% 139
0.56 IPS
 
Object Detection (F32)
100% 1347
47.3 IPS
 
Object Detection (F16)
99% 1497
52.5 IPS
 
Object Detection (I8)
52% 562
19.7 IPS
 
Face Detection (F32)
100% 3202
36.8 IPS
 
Face Detection (F16)
97% 5056
58.1 IPS
 
Face Detection (I8)
75% 533
6.13 IPS
 
Text Classification (F32)
100% 647
256.0 IPS
 
Text Classification (F16)
98% 780
308.6 IPS
 
Machine Translation (F32)
100% 986
151.9 IPS
 
Machine Translation (F16)
100% 968
149.2 IPS
 

Compare

Set Baseline Geekbench 6 now available