Geekbench ML Score

1119
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 26 2022 08:18 AM
Views 1

System Information

System Information
Operating System iOS 16.0
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 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 GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 640
68.5 IPS
 
Image Classification (F16)
100% 1044
111.8 IPS
 
Image Classification (I8)
81% 401
43.0 IPS
 
Image Segmentation (F32)
100% 3029
18.7 IPS
 
Image Segmentation (F16)
100% 4796
29.6 IPS
 
Image Segmentation (I8)
89% 737
4.55 IPS
 
Pose Estimation (F32)
100% 1194
4.83 IPS
 
Pose Estimation (F16)
100% 3386
13.7 IPS
 
Pose Estimation (I8)
80% 138
0.56 IPS
 
Object Detection (F32)
100% 1439
50.5 IPS
 
Object Detection (F16)
99% 1522
53.4 IPS
 
Object Detection (I8)
52% 560
19.6 IPS
 
Face Detection (F32)
100% 3179
36.5 IPS
 
Face Detection (F16)
97% 5068
58.2 IPS
 
Face Detection (I8)
75% 536
6.16 IPS
 
Text Classification (F32)
100% 653
258.1 IPS
 
Text Classification (F16)
98% 793
313.5 IPS
 
Machine Translation (F32)
100% 984
151.7 IPS
 
Machine Translation (F16)
100% 982
151.4 IPS
 

Compare

Set Baseline Geekbench 6 now available