Geekbench ML Score

488
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date November 24 2022 06:50 PM
Views 1

System Information

System Information
Operating System iOS 16.2
Model iPad Pro (12.9-inch 5th generation)
Model IDiPad13,11
Motherboard J523xAP
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 15.34 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 539
57.8 IPS
 
Image Classification (F16)
100% 251
26.9 IPS
 
Image Classification (I8)
81% 180
19.3 IPS
 
Image Segmentation (F32)
100% 326
2.02 IPS
 
Image Segmentation (F16)
100% 420
2.59 IPS
 
Image Segmentation (I8)
89% 650
4.02 IPS
 
Pose Estimation (F32)
100% 190
0.77 IPS
 
Pose Estimation (F16)
100% 332
1.34 IPS
 
Pose Estimation (I8)
80% 254
1.03 IPS
 
Object Detection (F32)
100% 446
15.6 IPS
 
Object Detection (F16)
100% 454
15.9 IPS
 
Object Detection (I8)
52% 307
10.8 IPS
 
Face Detection (F32)
100% 1033
11.9 IPS
 
Face Detection (F16)
100% 597
6.86 IPS
 
Face Detection (I8)
75% 807
9.27 IPS
 
Text Classification (F32)
100% 540
213.7 IPS
 
Text Classification (F16)
100% 649
256.5 IPS
 
Machine Translation (F32)
100% 1750
269.7 IPS
 
Machine Translation (F16)
100% 1870
288.2 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download