Geekbench ML Score

1401
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date May 17 2022 11:20 AM
Views 1

System Information

System Information
Operating System iOS 15.4.1
Model iPhone 11 Pro
Model IDiPhone12,3
Motherboard D421AP
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 3.68 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 1548
165.9 IPS
 
Image Classification (F16)
100% 1585
169.9 IPS
 
Image Classification (I8)
81% 448
48.0 IPS
 
Image Segmentation (F32)
100% 3439
21.2 IPS
 
Image Segmentation (F16)
100% 5418
33.5 IPS
 
Image Segmentation (I8)
89% 837
5.17 IPS
 
Pose Estimation (F32)
100% 1423
5.76 IPS
 
Pose Estimation (F16)
100% 4444
18.0 IPS
 
Pose Estimation (I8)
80% 154
0.62 IPS
 
Object Detection (F32)
100% 1492
52.4 IPS
 
Object Detection (F16)
99% 1869
65.6 IPS
 
Object Detection (I8)
52% 641
22.5 IPS
 
Face Detection (F32)
100% 3628
41.7 IPS
 
Face Detection (F16)
97% 5357
61.6 IPS
 
Face Detection (I8)
75% 636
7.31 IPS
 
Text Classification (F32)
100% 966
382.2 IPS
 
Text Classification (F16)
98% 1202
475.6 IPS
 
Machine Translation (F32)
100% 1202
185.3 IPS
 
Machine Translation (F16)
100% 1192
183.7 IPS
 

Compare

Set Baseline Geekbench 6 now available