Geekbench ML Score

289
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64

Result Information

User HWFF
Upload Date January 21 2024 04:17 PM
Views 1

System Information

System Information
Operating System Android 10
Model Huawei P30 Pro
Model IDHUAWEI VOG-L29
Motherboard VOG
CPU Information
Name vendor
Topology 1 Processor, 8 Cores
Identifier ARM implementer 72 architecture 8 variant 1 part 3392 revision 0
Base Frequency 1.80 GHz
Cluster 14 Cores @ 1.80 GHz
Cluster 22 Cores @ 1.92 GHz
Cluster 32 Cores @ 2.60 GHz
Memory Information
Size 7.43 GB
Inference Information
Framework TensorFlow Lite
Backend NNAPI
Device

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 172
18.5 IPS
 
Image Classification (F16)
99% 124
13.3 IPS
 
Image Classification (I8)
81% 216
23.1 IPS
 
Image Segmentation (F32)
100% 309
1.91 IPS
 
Image Segmentation (F16)
100% 310
1.91 IPS
 
Image Segmentation (I8)
89% 403
2.49 IPS
 
Pose Estimation (F32)
100% 177
0.72 IPS
 
Pose Estimation (F16)
100% 1291
5.22 IPS
 
Pose Estimation (I8)
80% 64
0.26 IPS
 
Object Detection (F32)
100% 217
7.62 IPS
 
Object Detection (F16)
99% 359
12.6 IPS
 
Object Detection (I8)
52% 264
9.28 IPS
 
Face Detection (F32)
100% 245
2.81 IPS
 
Face Detection (F16)
100% 316
3.63 IPS
 
Face Detection (I8)
75% 304
3.49 IPS
 
Text Classification (F32)
100% 556
219.8 IPS
 
Text Classification (F16)
100% 556
219.8 IPS
 
Machine Translation (F32)
100% 395
60.8 IPS
 
Machine Translation (F16)
100% 394
60.8 IPS
 

Compare

Set Baseline Geekbench 6 now available