Geekbench ML Score

568
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

Upload Date October 23 2021 07:03 AM
Views 1

System Information

System Information
Operating System iOS 14.8
Model iPhone XS
Model IDiPhone11,2
Motherboard D321AP
CPU Information
Name Apple A12 Bionic
Topology 1 Processor, 6 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 3.70 GB
Inference Information
Framework TensorFlow Lite
Backend CPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 480
51.4 IPS
 
Image Classification (F16)
100% 479
51.3 IPS
 
Image Classification (I8)
81% 275
29.4 IPS
 
Image Segmentation (F32)
100% 769
4.75 IPS
 
Image Segmentation (F16)
100% 762
4.71 IPS
 
Image Segmentation (I8)
89% 978
6.04 IPS
 
Pose Estimation (F32)
100% 247
1.00 IPS
 
Pose Estimation (F16)
100% 248
1.00 IPS
 
Pose Estimation (I8)
80% 191
0.77 IPS
 
Object Detection (F32)
100% 677
23.8 IPS
 
Object Detection (F16)
100% 673
23.6 IPS
 
Object Detection (I8)
52% 542
19.0 IPS
 
Face Detection (F32)
100% 760
8.74 IPS
 
Face Detection (F16)
100% 755
8.67 IPS
 
Face Detection (I8)
75% 607
6.98 IPS
 
Text Classification (F32)
100% 781
308.8 IPS
 
Text Classification (F16)
100% 788
311.9 IPS
 
Machine Translation (F32)
100% 992
152.9 IPS
 
Machine Translation (F16)
100% 992
152.8 IPS
 

Compare

Set Baseline

Share

Geekbench ML now available for download