Geekbench ML Score

806
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 17 2021 12:41 PM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPhone X
Model IDiPhone10,6
Motherboard D221AP
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 2.76 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 647
69.4 IPS
 
Image Classification (F16)
100% 802
86.0 IPS
 
Image Classification (I8)
81% 292
31.3 IPS
 
Image Segmentation (F32)
100% 1918
11.8 IPS
 
Image Segmentation (F16)
100% 3520
21.7 IPS
 
Image Segmentation (I8)
89% 502
3.10 IPS
 
Pose Estimation (F32)
100% 632
2.56 IPS
 
Pose Estimation (F16)
100% 2211
8.95 IPS
 
Pose Estimation (I8)
80% 97
0.39 IPS
 
Object Detection (F32)
100% 1205
42.3 IPS
 
Object Detection (F16)
99% 1307
45.9 IPS
 
Object Detection (I8)
52% 397
13.9 IPS
 
Face Detection (F32)
100% 1945
22.3 IPS
 
Face Detection (F16)
97% 3919
45.0 IPS
 
Face Detection (I8)
75% 387
4.45 IPS
 
Text Classification (F32)
100% 487
192.6 IPS
 
Text Classification (F16)
98% 706
279.2 IPS
 
Machine Translation (F32)
100% 618
95.3 IPS
 
Machine Translation (F16)
100% 621
95.7 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download