Geekbench ML Score

820
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 26 2022 10:04 PM
Views 1

System Information

System Information
Operating System iOS 16.0.2
Model iPhone 8
Model IDiPhone10,1
Motherboard D20AP
CPU Information
Name Apple A11 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 2.39 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 1.93 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 752
80.6 IPS
 
Image Classification (F16)
100% 856
91.7 IPS
 
Image Classification (I8)
81% 351
37.6 IPS
 
Image Segmentation (F32)
100% 1999
12.3 IPS
 
Image Segmentation (F16)
100% 3520
21.7 IPS
 
Image Segmentation (I8)
89% 613
3.79 IPS
 
Pose Estimation (F32)
100% 642
2.60 IPS
 
Pose Estimation (F16)
100% 2165
8.76 IPS
 
Pose Estimation (I8)
80% 101
0.41 IPS
 
Object Detection (F32)
100% 1166
40.9 IPS
 
Object Detection (F16)
99% 1159
40.7 IPS
 
Object Detection (I8)
52% 397
13.9 IPS
 
Face Detection (F32)
100% 1914
22.0 IPS
 
Face Detection (F16)
97% 4082
46.9 IPS
 
Face Detection (I8)
75% 379
4.36 IPS
 
Text Classification (F32)
100% 453
179.1 IPS
 
Text Classification (F16)
98% 674
266.7 IPS
 
Machine Translation (F32)
100% 591
91.0 IPS
 
Machine Translation (F16)
100% 588
90.6 IPS
 

Compare

Set Baseline Geekbench 6 now available