Geekbench ML Score

1845
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date July 16 2022 03:29 PM
Views 1

System Information

System Information
Operating System iOS 16.0
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 3.57 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1712
183.5 IPS
 
Image Classification (F16)
100% 1615
173.1 IPS
 
Image Classification (I8)
81% 618
66.3 IPS
 
Image Segmentation (F32)
100% 5304
32.8 IPS
 
Image Segmentation (F16)
100% 7190
44.4 IPS
 
Image Segmentation (I8)
89% 1132
6.99 IPS
 
Pose Estimation (F32)
100% 1761
7.12 IPS
 
Pose Estimation (F16)
100% 4170
16.9 IPS
 
Pose Estimation (I8)
80% 222
0.90 IPS
 
Object Detection (F32)
100% 1646
57.8 IPS
 
Object Detection (F16)
100% 2964
104.0 IPS
 
Object Detection (I8)
52% 929
32.6 IPS
 
Face Detection (F32)
100% 4815
55.3 IPS
 
Face Detection (F16)
97% 5837
67.1 IPS
 
Face Detection (I8)
75% 889
10.2 IPS
 
Text Classification (F32)
100% 1796
710.2 IPS
 
Text Classification (F16)
100% 1125
445.0 IPS
 
Machine Translation (F32)
100% 2029
312.8 IPS
 
Machine Translation (F16)
100% 2032
313.2 IPS
 

Compare

Set Baseline