Geekbench ML Score

1137
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 09 2022 12:10 AM
Views 1

System Information

System Information
Operating System iOS 16.2
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 GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 686
73.5 IPS
 
Image Classification (F16)
100% 1047
112.2 IPS
 
Image Classification (I8)
81% 402
43.1 IPS
 
Image Segmentation (F32)
100% 3065
18.9 IPS
 
Image Segmentation (F16)
100% 4792
29.6 IPS
 
Image Segmentation (I8)
89% 736
4.54 IPS
 
Pose Estimation (F32)
100% 1207
4.88 IPS
 
Pose Estimation (F16)
100% 3446
13.9 IPS
 
Pose Estimation (I8)
80% 139
0.56 IPS
 
Object Detection (F32)
100% 1536
53.9 IPS
 
Object Detection (F16)
99% 1507
52.9 IPS
 
Object Detection (I8)
52% 541
19.0 IPS
 
Face Detection (F32)
100% 3175
36.5 IPS
 
Face Detection (F16)
97% 5191
59.6 IPS
 
Face Detection (I8)
75% 535
6.14 IPS
 
Text Classification (F32)
100% 688
272.3 IPS
 
Text Classification (F16)
98% 876
346.6 IPS
 
Machine Translation (F32)
100% 990
152.6 IPS
 
Machine Translation (F16)
100% 975
150.3 IPS
 

Compare

Set Baseline