Geekbench ML Score

488
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date January 25 2023 09:52 AM
Views 3

System Information

System Information
Operating System iOS 15.7.2
Model iPhone SE
Model IDiPhone8,4
Motherboard N69AP
CPU Information
Name Apple A9
Topology 1 Processor, 2 Cores
Identifier ARM
Base Frequency 1.80 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% 425
45.5 IPS
 
Image Classification (F16)
100% 640
68.6 IPS
 
Image Classification (I8)
81% 191
20.4 IPS
 
Image Segmentation (F32)
100% 953
5.89 IPS
 
Image Segmentation (F16)
100% 1579
9.75 IPS
 
Image Segmentation (I8)
89% 361
2.23 IPS
 
Pose Estimation (F32)
100% 392
1.59 IPS
 
Pose Estimation (F16)
100% 652
2.64 IPS
 
Pose Estimation (I8)
80% 66
0.27 IPS
 
Object Detection (F32)
100% 565
19.8 IPS
 
Object Detection (F16)
100% 879
30.9 IPS
 
Object Detection (I8)
52% 273
9.57 IPS
 
Face Detection (F32)
100% 903
10.4 IPS
 
Face Detection (F16)
97% 1573
18.1 IPS
 
Face Detection (I8)
75% 266
3.06 IPS
 
Text Classification (F32)
100% 421
166.4 IPS
 
Text Classification (F16)
98% 586
231.7 IPS
 
Machine Translation (F32)
100% 445
68.6 IPS
 
Machine Translation (F16)
100% 456
70.2 IPS
 

Compare

Set Baseline Geekbench 6 now available