Geekbench ML Score

817
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 03 2021 11:02 AM
Views 1

System Information

System Information
Operating System iOS 15.0.2
Model iPhone 8
Model IDiPhone10,4
Motherboard D201AP
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% 716
76.7 IPS
 
Image Classification (F16)
100% 952
102.0 IPS
 
Image Classification (I8)
81% 359
38.4 IPS
 
Image Segmentation (F32)
100% 2007
12.4 IPS
 
Image Segmentation (F16)
100% 3530
21.8 IPS
 
Image Segmentation (I8)
89% 658
4.06 IPS
 
Pose Estimation (F32)
100% 643
2.60 IPS
 
Pose Estimation (F16)
100% 2173
8.79 IPS
 
Pose Estimation (I8)
80% 128
0.52 IPS
 
Object Detection (F32)
100% 1290
45.3 IPS
 
Object Detection (F16)
99% 1340
47.0 IPS
 
Object Detection (I8)
52% 391
13.7 IPS
 
Face Detection (F32)
100% 1741
20.0 IPS
 
Face Detection (F16)
97% 3367
38.7 IPS
 
Face Detection (I8)
75% 274
3.15 IPS
 
Text Classification (F32)
100% 481
190.1 IPS
 
Text Classification (F16)
98% 685
271.0 IPS
 
Machine Translation (F32)
100% 479
73.8 IPS
 
Machine Translation (F16)
100% 615
94.8 IPS
 

Compare

Set Baseline Geekbench 6 now available