Geekbench ML Score

2859
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date December 08 2022 08:44 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,8
Motherboard J522AP
CPU Information
Name Apple M1
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 3.19 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 7.31 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4249
455.3 IPS
 
Image Classification (F16)
100% 5981
640.8 IPS
 
Image Classification (I8)
81% 675
72.3 IPS
 
Image Segmentation (F32)
100% 8082
49.9 IPS
 
Image Segmentation (F16)
100% 11889
73.4 IPS
 
Image Segmentation (I8)
89% 1233
7.62 IPS
 
Pose Estimation (F32)
100% 2862
11.6 IPS
 
Pose Estimation (F16)
100% 6802
27.5 IPS
 
Pose Estimation (I8)
80% 236
0.96 IPS
 
Object Detection (F32)
100% 3650
128.1 IPS
 
Object Detection (F16)
100% 3864
135.6 IPS
 
Object Detection (I8)
52% 965
33.9 IPS
 
Face Detection (F32)
100% 7021
80.7 IPS
 
Face Detection (F16)
97% 12442
142.9 IPS
 
Face Detection (I8)
75% 949
10.9 IPS
 
Text Classification (F32)
100% 3399
1.34 KIPS
 
Text Classification (F16)
100% 3725
1.47 KIPS
 
Machine Translation (F32)
100% 1878
289.4 IPS
 
Machine Translation (F16)
100% 1868
288.0 IPS
 

Compare

Set Baseline