Geekbench ML Score

562
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date December 07 2024 09:04 AM
Views 3

System Information

System Information
Operating System iOS 16.7.10
Model iPad Pro (9.7-inch)
Model IDiPad6,4
Motherboard J128AP
CPU Information
Name Apple A9X
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 2.26 GHz
Cluster 12 Cores
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.92 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 225
42.1 IPS
 
Image Classification (F16)
100% 216
40.4 IPS
 
Image Classification (I8)
99% 204
38.2 IPS
 
Image Segmentation (F32)
100% 170
2.84 IPS
 
Image Segmentation (F16)
100% 172
2.88 IPS
 
Image Segmentation (I8)
100% 175
2.92 IPS
 
Pose Estimation (F32)
100% 2053
2.49 IPS
 
Pose Estimation (F16)
100% 2016
2.44 IPS
 
Pose Estimation (I8)
100% 2025
2.45 IPS
 
Object Detection (F32)
100% 298
22.2 IPS
 
Object Detection (F16)
100% 271
20.3 IPS
 
Object Detection (I8)
97% 299
22.3 IPS
 
Face Detection (F32)
100% 1229
14.6 IPS
 
Face Detection (F16)
100% 1166
13.9 IPS
 
Face Detection (I8)
99% 1158
13.8 IPS
 
Depth Estimation (F32)
100% 2286
17.7 IPS
 
Depth Estimation (F16)
100% 2117
16.4 IPS
 
Depth Estimation (I8)
99% 2168
16.8 IPS
 
Style Transfer (F32)
100% 5391
7.09 IPS
 
Style Transfer (F16)
100% 4808
6.32 IPS
 
Style Transfer (I8)
100% 4710
6.20 IPS
 
Image Super-Resolution (F32)
100% 1156
41.3 IPS
 
Image Super-Resolution (F16)
100% 1115
39.8 IPS
 
Image Super-Resolution (I8)
100% 1156
41.3 IPS
 
Text Classification (F32)
100% 53
76.0 IPS
 
Text Classification (F16)
100% 97
139.8 IPS
 
Text Classification (I8)
96% 97
139.4 IPS
 
Machine Translation (F32)
100% 131
2.41 IPS
 
Machine Translation (F16)
100% 112
2.05 IPS
 
Machine Translation (I8)
99% 132
2.42 IPS
 

Compare

Set Baseline Geekbench 6 now available