Geekbench ML Score

2444
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date April 21 2022 05:52 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone 13 Pro
Model IDiPhone14,2
Motherboard D63AP
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 5.52 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2875
308.0 IPS
 
Image Classification (F16)
100% 4678
501.2 IPS
 
Image Classification (I8)
81% 672
72.0 IPS
 
Image Segmentation (F32)
100% 5935
36.7 IPS
 
Image Segmentation (F16)
100% 8353
51.6 IPS
 
Image Segmentation (I8)
89% 1205
7.44 IPS
 
Pose Estimation (F32)
100% 1921
7.77 IPS
 
Pose Estimation (F16)
100% 4890
19.8 IPS
 
Pose Estimation (I8)
80% 233
0.94 IPS
 
Object Detection (F32)
100% 3742
131.3 IPS
 
Object Detection (F16)
100% 5088
178.5 IPS
 
Object Detection (I8)
52% 967
33.9 IPS
 
Face Detection (F32)
100% 5090
58.5 IPS
 
Face Detection (F16)
97% 9351
107.4 IPS
 
Face Detection (I8)
75% 900
10.3 IPS
 
Text Classification (F32)
100% 2468
976.2 IPS
 
Text Classification (F16)
100% 2695
1.07 KIPS
 
Machine Translation (F32)
100% 1953
301.0 IPS
 
Machine Translation (F16)
100% 1958
301.8 IPS
 

Compare

Set Baseline Geekbench 6 now available