Geekbench ML Score

639
Core ML GPU Inference Score
Geekbench ML 0.6.0 for iOS AArch64

Result Information

Upload Date August 26 2024 10:44 AM
Views 3

System Information

System Information
Operating System iOS 16.7.8
Model iPad Pro (12.9-inch)
Model IDiPad6,7
Motherboard J98aAP
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 3.90 GB
Inference Information
Framework Core ML
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 309
57.8 IPS
 
Image Classification (F16)
100% 293
54.9 IPS
 
Image Classification (I8)
99% 283
52.9 IPS
 
Image Segmentation (F32)
100% 185
3.08 IPS
 
Image Segmentation (F16)
100% 182
3.03 IPS
 
Image Segmentation (I8)
100% 185
3.10 IPS
 
Pose Estimation (F32)
100% 2022
2.45 IPS
 
Pose Estimation (F16)
100% 1994
2.42 IPS
 
Pose Estimation (I8)
100% 1991
2.41 IPS
 
Object Detection (F32)
100% 394
29.4 IPS
 
Object Detection (F16)
100% 367
27.4 IPS
 
Object Detection (I8)
97% 297
22.2 IPS
 
Face Detection (F32)
100% 1403
16.7 IPS
 
Face Detection (F16)
100% 1345
16.0 IPS
 
Face Detection (I8)
99% 1346
16.0 IPS
 
Depth Estimation (F32)
100% 2245
17.4 IPS
 
Depth Estimation (F16)
100% 2227
17.3 IPS
 
Depth Estimation (I8)
99% 2224
17.2 IPS
 
Style Transfer (F32)
100% 5571
7.33 IPS
 
Style Transfer (F16)
100% 5517
7.26 IPS
 
Style Transfer (I8)
100% 5523
7.26 IPS
 
Image Super-Resolution (F32)
100% 1112
39.7 IPS
 
Image Super-Resolution (F16)
100% 1147
41.0 IPS
 
Image Super-Resolution (I8)
100% 968
34.6 IPS
 
Text Classification (F32)
100% 60
86.4 IPS
 
Text Classification (F16)
100% 104
149.8 IPS
 
Text Classification (I8)
96% 105
151.5 IPS
 
Machine Translation (F32)
100% 210
3.86 IPS
 
Machine Translation (F16)
100% 170
3.12 IPS
 
Machine Translation (I8)
99% 201
3.71 IPS
 

Compare

Set Baseline Geekbench 6 now available