Geekbench ML Score

1840
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 11:05 PM
Views 1

System Information

System Information
Operating System iOS 16.1.2
Model iPhone 13
Model IDiPhone14,5
Motherboard D17AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.56 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1432
153.4 IPS
 
Image Classification (F16)
100% 2571
275.5 IPS
 
Image Classification (I8)
81% 681
72.9 IPS
 
Image Segmentation (F32)
100% 5241
32.4 IPS
 
Image Segmentation (F16)
100% 7208
44.5 IPS
 
Image Segmentation (I8)
89% 1189
7.34 IPS
 
Pose Estimation (F32)
100% 1763
7.14 IPS
 
Pose Estimation (F16)
100% 4198
17.0 IPS
 
Pose Estimation (I8)
80% 229
0.93 IPS
 
Object Detection (F32)
100% 1598
56.1 IPS
 
Object Detection (F16)
100% 3169
111.2 IPS
 
Object Detection (I8)
52% 961
33.7 IPS
 
Face Detection (F32)
100% 4801
55.2 IPS
 
Face Detection (F16)
97% 5860
67.3 IPS
 
Face Detection (I8)
75% 898
10.3 IPS
 
Text Classification (F32)
100% 984
389.2 IPS
 
Text Classification (F16)
100% 1121
443.3 IPS
 
Machine Translation (F32)
100% 2043
314.9 IPS
 
Machine Translation (F16)
100% 2043
314.9 IPS
 

Compare

Set Baseline