Geekbench ML Score

1073
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date January 17 2024 09:13 PM
Views 1

System Information

System Information
Operating System Android 13
Model HONOR VER-N49
Model IDHONOR VER-N49
Motherboard kalama
Governorwalt
CPU Information
Name ARM ARMv8
Topology 1 Processor, 8 Cores
Identifier ARM implementer 65 architecture 8 variant 1 part 3406 revision 0
Base Frequency 2.02 GHz
Cluster 13 Cores @ 2.02 GHz
Cluster 24 Cores @ 2.80 GHz
Cluster 31 Core @ 3.19 GHz
Memory Information
Size 14.95 GB
Inference Information
Framework TensorFlow Lite
Backend GPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 615
115.0 IPS
 
Image Classification (F16)
100% 1020
190.9 IPS
 
Image Classification (I8)
99% 971
181.8 IPS
 
Image Segmentation (F32)
100% 1220
20.4 IPS
 
Image Segmentation (F16)
100% 1943
32.4 IPS
 
Image Segmentation (I8)
98% 1852
30.9 IPS
 
Pose Estimation (F32)
100% 930
1.13 IPS
 
Pose Estimation (F16)
100% 1384
1.68 IPS
 
Pose Estimation (I8)
100% 1382
1.67 IPS
 
Object Detection (F32)
100% 397
29.7 IPS
 
Object Detection (F16)
100% 573
42.8 IPS
 
Object Detection (I8)
62% 498
37.2 IPS
 
Face Detection (F32)
100% 2116
25.2 IPS
 
Face Detection (F16)
97% 3377
40.2 IPS
 
Face Detection (I8)
86% 2980
35.4 IPS
 
Depth Estimation (F32)
100% 1438
11.2 IPS
 
Depth Estimation (F16)
100% 2752
21.3 IPS
 
Depth Estimation (I8)
95% 2717
21.1 IPS
 
Style Transfer (F32)
100% 3583
4.71 IPS
 
Style Transfer (F16)
100% 8061
10.6 IPS
 
Style Transfer (I8)
98% 8087
10.6 IPS
 
Image Super-Resolution (F32)
100% 470
16.8 IPS
 
Image Super-Resolution (F16)
100% 418
14.9 IPS
 
Image Super-Resolution (I8)
98% 413
14.7 IPS
 
Text Classification (F32)
100% 327
470.5 IPS
 
Text Classification (F16)
100% 326
468.9 IPS
 
Text Classification (I8)
92% 201
289.5 IPS
 
Machine Translation (F32)
100% 556
10.2 IPS
 
Machine Translation (F16)
100% 557
10.3 IPS
 
Machine Translation (I8)
64% 545
10.0 IPS
 

Compare

Set Baseline Geekbench 6 now available