Geekbench ML Score

1613
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 14 2022 10:11 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone 12
Model IDiPhone13,2
Motherboard D53gAP
CPU Information
Name Apple A14 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.99 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.58 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1497
160.4 IPS
 
Image Classification (F16)
100% 1665
178.4 IPS
 
Image Classification (I8)
81% 639
68.4 IPS
 
Image Segmentation (F32)
100% 4207
26.0 IPS
 
Image Segmentation (F16)
100% 5853
36.2 IPS
 
Image Segmentation (I8)
89% 1091
6.74 IPS
 
Pose Estimation (F32)
100% 1491
6.03 IPS
 
Pose Estimation (F16)
100% 4991
20.2 IPS
 
Pose Estimation (I8)
80% 214
0.87 IPS
 
Object Detection (F32)
100% 1620
56.9 IPS
 
Object Detection (F16)
99% 1695
59.5 IPS
 
Object Detection (I8)
52% 909
31.9 IPS
 
Face Detection (F32)
100% 4283
49.2 IPS
 
Face Detection (F16)
97% 5368
61.7 IPS
 
Face Detection (I8)
75% 863
9.92 IPS
 
Text Classification (F32)
100% 855
338.2 IPS
 
Text Classification (F16)
98% 1094
432.7 IPS
 
Machine Translation (F32)
100% 1666
256.7 IPS
 
Machine Translation (F16)
100% 1677
258.5 IPS
 

Compare

Set Baseline Geekbench 6 now available