Geekbench ML Score

1854
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date August 06 2022 01:12 AM
Views 1

System Information

System Information
Operating System iOS 16.0
Model iPad Pro 11-inch (2nd generation)
Model IDiPad8,10
Motherboard J418AP
CPU Information
Name Apple A12Z Bionic
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache48.0 KB x 1
L1 Data Cache32.0 KB x 1
L2 Cache2.00 MB x 1
Memory Information
Size 5.57 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2937
314.7 IPS
 
Image Classification (F16)
100% 4537
486.1 IPS
 
Image Classification (I8)
81% 402
43.0 IPS
 
Image Segmentation (F32)
100% 5812
35.9 IPS
 
Image Segmentation (F16)
100% 9771
60.4 IPS
 
Image Segmentation (I8)
89% 748
4.62 IPS
 
Pose Estimation (F32)
100% 1986
8.04 IPS
 
Pose Estimation (F16)
100% 6398
25.9 IPS
 
Pose Estimation (I8)
80% 142
0.57 IPS
 
Object Detection (F32)
100% 2658
93.3 IPS
 
Object Detection (F16)
99% 2664
93.5 IPS
 
Object Detection (I8)
52% 560
19.7 IPS
 
Face Detection (F32)
100% 5442
62.5 IPS
 
Face Detection (F16)
97% 10590
121.7 IPS
 
Face Detection (I8)
75% 552
6.35 IPS
 
Text Classification (F32)
100% 1631
645.1 IPS
 
Text Classification (F16)
98% 1565
619.2 IPS
 
Machine Translation (F32)
100% 971
149.6 IPS
 
Machine Translation (F16)
100% 970
149.5 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download