Geekbench ML Score

2753
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 04:06 AM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,4
Motherboard J517AP
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 7.35 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4038
432.7 IPS
 
Image Classification (F16)
100% 5649
605.2 IPS
 
Image Classification (I8)
81% 675
72.3 IPS
 
Image Segmentation (F32)
100% 7928
49.0 IPS
 
Image Segmentation (F16)
100% 11749
72.6 IPS
 
Image Segmentation (I8)
89% 1232
7.61 IPS
 
Pose Estimation (F32)
100% 2859
11.6 IPS
 
Pose Estimation (F16)
100% 6818
27.6 IPS
 
Pose Estimation (I8)
80% 236
0.95 IPS
 
Object Detection (F32)
100% 3324
116.6 IPS
 
Object Detection (F16)
100% 3485
122.3 IPS
 
Object Detection (I8)
52% 952
33.4 IPS
 
Face Detection (F32)
100% 7059
81.1 IPS
 
Face Detection (F16)
97% 12351
141.9 IPS
 
Face Detection (I8)
75% 947
10.9 IPS
 
Text Classification (F32)
100% 2841
1.12 KIPS
 
Text Classification (F16)
100% 3256
1.29 KIPS
 
Machine Translation (F32)
100% 1823
281.0 IPS
 
Machine Translation (F16)
100% 1822
280.9 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download