Geekbench ML Score

1135
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 15 2022 12:53 PM
Views 1

System Information

System Information
Operating System iOS 14.5.1
Model iPhone 11
Model IDiPhone12,1
Motherboard N104AP
CPU Information
Name Apple A13 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.66 GHz
L1 Instruction Cache96.0 KB x 1
L1 Data Cache48.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 3.77 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1621
173.7 IPS
 
Image Classification (F16)
100% 1563
167.5 IPS
 
Image Classification (I8)
81% 238
25.5 IPS
 
Image Segmentation (F32)
100% 3277
20.2 IPS
 
Image Segmentation (F16)
100% 5138
31.7 IPS
 
Image Segmentation (I8)
89% 458
2.83 IPS
 
Pose Estimation (F32)
100% 1418
5.74 IPS
 
Pose Estimation (F16)
100% 4221
17.1 IPS
 
Pose Estimation (I8)
80% 82
0.33 IPS
 
Object Detection (F32)
100% 1301
45.7 IPS
 
Object Detection (F16)
99% 1665
58.4 IPS
 
Object Detection (I8)
52% 481
16.9 IPS
 
Face Detection (F32)
100% 3490
40.1 IPS
 
Face Detection (F16)
97% 4989
57.3 IPS
 
Face Detection (I8)
75% 318
3.65 IPS
 
Text Classification (F32)
100% 953
377.0 IPS
 
Text Classification (F16)
98% 1165
460.7 IPS
 
Machine Translation (F32)
100% 964
148.6 IPS
 
Machine Translation (F16)
100% 795
122.6 IPS
 

Compare

Set Baseline Geekbench 6 now available