Geekbench ML Score

561
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.1 for iOS AArch64

Result Information

User Puffin
Upload Date August 09 2021 12:11 AM
Views 10

System Information

System Information
Operating System iOS 14.7.1
Model iPod (7th generation)
Model IDiPod9,1
Motherboard N112AP
CPU Information
Name Apple A10 Fusion
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.63 GHz
L1 Instruction Cache64.0 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache3.00 MB x 1
Memory Information
Size 1.97 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 544
58.2 IPS
 
Image Classification (F16)
100% 582
62.4 IPS
 
Image Classification (I8)
81% 226
24.2 IPS
 
Image Segmentation (F32)
100% 1139
7.04 IPS
 
Image Segmentation (F16)
100% 1854
11.4 IPS
 
Image Segmentation (I8)
89% 412
2.54 IPS
 
Pose Estimation (F32)
100% 499
2.02 IPS
 
Pose Estimation (F16)
100% 807
3.26 IPS
 
Pose Estimation (I8)
80% 88
0.36 IPS
 
Object Detection (F32)
100% 692
24.3 IPS
 
Object Detection (F16)
100% 1080
37.9 IPS
 
Object Detection (I8)
52% 323
11.3 IPS
 
Face Detection (F32)
100% 1128
13.0 IPS
 
Face Detection (F16)
97% 1920
22.1 IPS
 
Face Detection (I8)
75% 292
3.36 IPS
 
Text Classification (F32)
100% 400
158.2 IPS
 
Text Classification (F16)
98% 537
212.3 IPS
 
Machine Translation (F32)
100% 482
74.3 IPS
 
Machine Translation (F16)
100% 494
76.1 IPS
 

Compare

Set Baseline Geekbench 6 now available