Geekbench ML Score

1868
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 09 2022 06:42 AM
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% 1234
132.2 IPS
 
Image Classification (F16)
100% 2570
275.4 IPS
 
Image Classification (I8)
81% 671
71.9 IPS
 
Image Segmentation (F32)
100% 5189
32.1 IPS
 
Image Segmentation (F16)
100% 6893
42.6 IPS
 
Image Segmentation (I8)
89% 1144
7.06 IPS
 
Pose Estimation (F32)
100% 1769
7.16 IPS
 
Pose Estimation (F16)
100% 4207
17.0 IPS
 
Pose Estimation (I8)
80% 219
0.88 IPS
 
Object Detection (F32)
100% 2162
75.9 IPS
 
Object Detection (F16)
100% 3065
107.6 IPS
 
Object Detection (I8)
52% 911
32.0 IPS
 
Face Detection (F32)
100% 4848
55.7 IPS
 
Face Detection (F16)
97% 8391
96.4 IPS
 
Face Detection (I8)
75% 857
9.85 IPS
 
Text Classification (F32)
100% 1013
400.7 IPS
 
Text Classification (F16)
100% 1128
446.0 IPS
 
Machine Translation (F32)
100% 2060
317.5 IPS
 
Machine Translation (F16)
100% 2053
316.4 IPS
 

Compare

Set Baseline