Geekbench ML Score

638
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date September 17 2021 12:46 PM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPad Pro (12.9-inch 2nd Generation)
Model IDiPad7,2
Motherboard J121AP
CPU Information
Name Apple A10X Fusion
Topology 1 Processor, 3 Cores
Identifier ARM
Base Frequency 2.34 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache8.00 MB x 1
Memory Information
Size 3.88 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 381
40.8 IPS
 
Image Classification (F16)
100% 391
41.9 IPS
 
Image Classification (I8)
81% 830
89.0 IPS
 
Image Segmentation (F32)
100% 641
3.96 IPS
 
Image Segmentation (F16)
100% 640
3.95 IPS
 
Image Segmentation (I8)
89% 1486
9.18 IPS
 
Pose Estimation (F32)
100% 267
1.08 IPS
 
Pose Estimation (F16)
100% 266
1.08 IPS
 
Pose Estimation (I8)
80% 352
1.42 IPS
 
Object Detection (F32)
100% 635
22.3 IPS
 
Object Detection (F16)
100% 641
22.5 IPS
 
Object Detection (I8)
52% 1146
40.2 IPS
 
Face Detection (F32)
100% 849
9.75 IPS
 
Face Detection (F16)
100% 847
9.74 IPS
 
Face Detection (I8)
75% 1139
13.1 IPS
 
Text Classification (F32)
100% 695
274.8 IPS
 
Text Classification (F16)
100% 693
274.2 IPS
 
Machine Translation (F32)
100% 753
116.0 IPS
 
Machine Translation (F16)
100% 754
116.2 IPS
 

Compare

Set Baseline Geekbench 6 now available