Geekbench ML Score

1603
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date June 13 2021 07:40 AM
Views 1

System Information

System Information
Operating System iOS 14.6
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 3.62 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1661
177.9 IPS
 
Image Classification (F16)
100% 1692
181.3 IPS
 
Image Classification (I8)
81% 646
69.2 IPS
 
Image Segmentation (F32)
100% 3933
24.3 IPS
 
Image Segmentation (F16)
100% 5778
35.7 IPS
 
Image Segmentation (I8)
89% 1129
6.98 IPS
 
Pose Estimation (F32)
100% 1420
5.75 IPS
 
Pose Estimation (F16)
100% 4666
18.9 IPS
 
Pose Estimation (I8)
80% 212
0.86 IPS
 
Object Detection (F32)
100% 1729
60.7 IPS
 
Object Detection (F16)
99% 1695
59.5 IPS
 
Object Detection (I8)
52% 858
30.1 IPS
 
Face Detection (F32)
100% 3907
44.9 IPS
 
Face Detection (F16)
97% 5374
61.7 IPS
 
Face Detection (I8)
75% 847
9.73 IPS
 
Text Classification (F32)
100% 860
340.0 IPS
 
Text Classification (F16)
98% 1107
438.0 IPS
 
Machine Translation (F32)
100% 1684
259.5 IPS
 
Machine Translation (F16)
100% 1680
259.0 IPS
 

Compare

Set Baseline Geekbench 6 now available