Geekbench ML Score

2513
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date September 19 2022 07:29 AM
Views 7

System Information

System Information
Operating System iOS 16.0.1
Model iPhone15,2
Model IDiPhone15,2
Motherboard D73AP
CPU Information
Name ARM
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.44 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.51 GB
Inference Information
Framework TensorFlow Lite
Backend GPU

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2896
310.3 IPS
 
Image Classification (F16)
100% 4631
496.1 IPS
 
Image Classification (I8)
81% 743
79.6 IPS
 
Image Segmentation (F32)
100% 6546
40.4 IPS
 
Image Segmentation (F16)
100% 9395
58.0 IPS
 
Image Segmentation (I8)
89% 1350
8.34 IPS
 
Pose Estimation (F32)
100% 2374
9.61 IPS
 
Pose Estimation (F16)
100% 5089
20.6 IPS
 
Pose Estimation (I8)
80% 258
1.04 IPS
 
Object Detection (F32)
100% 3335
117.0 IPS
 
Object Detection (F16)
100% 3641
127.8 IPS
 
Object Detection (I8)
52% 1063
37.3 IPS
 
Face Detection (F32)
100% 5933
68.2 IPS
 
Face Detection (F16)
97% 9930
114.1 IPS
 
Face Detection (I8)
75% 1026
11.8 IPS
 
Text Classification (F32)
100% 2094
828.1 IPS
 
Text Classification (F16)
100% 1880
743.7 IPS
 
Machine Translation (F32)
100% 2248
346.4 IPS
 
Machine Translation (F16)
100% 2266
349.2 IPS
 

Compare

Set Baseline