Geekbench ML Score

1125
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 16 2022 11:40 AM
Views 1

System Information

System Information
Operating System iOS 15.4.1
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% 657
70.4 IPS
 
Image Classification (F16)
100% 1058
113.4 IPS
 
Image Classification (I8)
81% 400
42.9 IPS
 
Image Segmentation (F32)
100% 3066
18.9 IPS
 
Image Segmentation (F16)
100% 4596
28.4 IPS
 
Image Segmentation (I8)
89% 745
4.60 IPS
 
Pose Estimation (F32)
100% 1208
4.89 IPS
 
Pose Estimation (F16)
100% 3443
13.9 IPS
 
Pose Estimation (I8)
80% 141
0.57 IPS
 
Object Detection (F32)
100% 1378
48.4 IPS
 
Object Detection (F16)
99% 1607
56.4 IPS
 
Object Detection (I8)
52% 564
19.8 IPS
 
Face Detection (F32)
100% 3186
36.6 IPS
 
Face Detection (F16)
97% 5182
59.5 IPS
 
Face Detection (I8)
75% 543
6.24 IPS
 
Text Classification (F32)
100% 651
257.3 IPS
 
Text Classification (F16)
98% 780
308.7 IPS
 
Machine Translation (F32)
100% 983
151.5 IPS
 
Machine Translation (F16)
100% 984
151.7 IPS
 

Compare

Set Baseline Geekbench 6 now available