Geekbench ML Score

879
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date April 21 2022 10:08 PM
Views 1

System Information

System Information
Operating System iOS 15.4.1
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% 753
80.7 IPS
 
Image Classification (F16)
100% 934
100.1 IPS
 
Image Classification (I8)
81% 349
37.4 IPS
 
Image Segmentation (F32)
100% 2016
12.5 IPS
 
Image Segmentation (F16)
100% 3492
21.6 IPS
 
Image Segmentation (I8)
89% 626
3.87 IPS
 
Pose Estimation (F32)
100% 646
2.61 IPS
 
Pose Estimation (F16)
100% 2162
8.75 IPS
 
Pose Estimation (I8)
80% 120
0.49 IPS
 
Object Detection (F32)
100% 1241
43.6 IPS
 
Object Detection (F16)
99% 1297
45.5 IPS
 
Object Detection (I8)
52% 505
17.7 IPS
 
Face Detection (F32)
100% 2107
24.2 IPS
 
Face Detection (F16)
97% 4273
49.1 IPS
 
Face Detection (I8)
75% 438
5.03 IPS
 
Text Classification (F32)
100% 454
179.7 IPS
 
Text Classification (F16)
98% 675
267.0 IPS
 
Machine Translation (F32)
100% 700
107.8 IPS
 
Machine Translation (F16)
100% 706
108.9 IPS
 

Compare

Set Baseline Geekbench 6 now available