Geekbench ML Score

2842
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date October 14 2022 07:39 PM
Views 5

System Information

System Information
Operating System iOS 15.7
Model iPad Pro (11-inch 3rd generation)
Model IDiPad13,4
Motherboard J517AP
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 7.34 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 4099
439.2 IPS
 
Image Classification (F16)
100% 5873
629.2 IPS
 
Image Classification (I8)
81% 688
73.8 IPS
 
Image Segmentation (F32)
100% 8187
50.6 IPS
 
Image Segmentation (F16)
100% 11678
72.1 IPS
 
Image Segmentation (I8)
89% 1256
7.76 IPS
 
Pose Estimation (F32)
100% 2869
11.6 IPS
 
Pose Estimation (F16)
100% 6841
27.7 IPS
 
Pose Estimation (I8)
80% 241
0.97 IPS
 
Object Detection (F32)
100% 3519
123.5 IPS
 
Object Detection (F16)
100% 3510
123.2 IPS
 
Object Detection (I8)
52% 985
34.6 IPS
 
Face Detection (F32)
100% 7103
81.6 IPS
 
Face Detection (F16)
97% 12498
143.6 IPS
 
Face Detection (I8)
75% 964
11.1 IPS
 
Text Classification (F32)
100% 3398
1.34 KIPS
 
Text Classification (F16)
100% 3751
1.48 KIPS
 
Machine Translation (F32)
100% 1831
282.1 IPS
 
Machine Translation (F16)
100% 1831
282.2 IPS
 

Compare

Set Baseline Geekbench 6 now available