Geekbench ML Score

2456
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.2 for iOS AArch64

Result Information

Upload Date April 21 2022 05:56 PM
Views 1

System Information

System Information
Operating System iOS 15.5
Model iPhone 13 Pro
Model IDiPhone14,2
Motherboard D63AP
CPU Information
Name Apple A15 Bionic
Topology 1 Processor, 6 Cores
Identifier ARM
Base Frequency 3.23 GHz
L1 Instruction Cache128 KB x 1
L1 Data Cache64.0 KB x 1
L2 Cache4.00 MB x 1
Memory Information
Size 5.52 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 2885
309.1 IPS
 
Image Classification (F16)
100% 4358
467.0 IPS
 
Image Classification (I8)
81% 692
74.2 IPS
 
Image Segmentation (F32)
100% 5953
36.8 IPS
 
Image Segmentation (F16)
100% 8419
52.0 IPS
 
Image Segmentation (I8)
89% 1248
7.71 IPS
 
Pose Estimation (F32)
100% 1923
7.78 IPS
 
Pose Estimation (F16)
100% 4921
19.9 IPS
 
Pose Estimation (I8)
80% 240
0.97 IPS
 
Object Detection (F32)
100% 3753
131.7 IPS
 
Object Detection (F16)
100% 5109
179.3 IPS
 
Object Detection (I8)
52% 991
34.8 IPS
 
Face Detection (F32)
100% 5199
59.7 IPS
 
Face Detection (F16)
97% 9386
107.8 IPS
 
Face Detection (I8)
75% 927
10.7 IPS
 
Text Classification (F32)
100% 2430
961.3 IPS
 
Text Classification (F16)
100% 2651
1.05 KIPS
 
Machine Translation (F32)
100% 1948
300.3 IPS
 
Machine Translation (F16)
100% 1954
301.1 IPS
 

Compare

Set Baseline Geekbench 6 now available