Geekbench ML Score

692
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date June 12 2021 09:44 PM
Views 1

System Information

System Information
Operating System iOS 14.6
Model iPad Pro 12.9-inch (4th generation)
Model IDiPad8,11
Motherboard J420AP
CPU Information
Name Apple A12Z Bionic
Topology 1 Processor, 8 Cores
Identifier ARM
Base Frequency 2.49 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache128 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 5.54 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 649
69.5 IPS
 
Image Classification (F16)
100% 655
70.2 IPS
 
Image Classification (I8)
81% 222
23.7 IPS
 
Image Segmentation (F32)
100% 935
5.77 IPS
 
Image Segmentation (F16)
100% 930
5.75 IPS
 
Image Segmentation (I8)
89% 1202
7.43 IPS
 
Pose Estimation (F32)
100% 452
1.83 IPS
 
Pose Estimation (F16)
100% 451
1.83 IPS
 
Pose Estimation (I8)
80% 473
1.91 IPS
 
Object Detection (F32)
100% 992
34.8 IPS
 
Object Detection (F16)
100% 993
34.8 IPS
 
Object Detection (I8)
52% 457
16.0 IPS
 
Face Detection (F32)
100% 1177
13.5 IPS
 
Face Detection (F16)
100% 1175
13.5 IPS
 
Face Detection (I8)
75% 704
8.09 IPS
 
Text Classification (F32)
100% 468
185.1 IPS
 
Text Classification (F16)
100% 475
187.9 IPS
 
Machine Translation (F32)
100% 1007
155.3 IPS
 
Machine Translation (F16)
100% 1008
155.3 IPS
 

Compare

Set Baseline Geekbench 6 now available