Geekbench ML Score

550
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64

Result Information

Upload Date July 18 2024 03:17 PM
Views 1

System Information

System Information
Operating System Android 13
Model OnePlus 7 Pro
Model IDOnePlus GM1911
Motherboard msmnile
Governorschedutil
CPU Information
Name Qualcomm Qualcomm
Topology 1 Processor, 8 Cores
Identifier ARM implementer 81 architecture 8 variant 13 part 2052 revision 14
Base Frequency 1.78 GHz
Cluster 14 Cores @ 1.79 GHz
Cluster 23 Cores @ 2.42 GHz
Cluster 31 Core @ 2.84 GHz
Memory Information
Size 7.28 GB
Inference Information
Framework TensorFlow Lite
Backend CPU
Device Default

Inference Performance

Workload Accuracy Score
Image Classification (F32)
100% 250
46.8 IPS
 
Image Classification (F16)
100% 238
44.5 IPS
 
Image Classification (I8)
97% 453
84.8 IPS
 
Image Segmentation (F32)
100% 338
5.65 IPS
 
Image Segmentation (F16)
100% 342
5.71 IPS
 
Image Segmentation (I8)
98% 385
6.43 IPS
 
Pose Estimation (F32)
100% 572
0.69 IPS
 
Pose Estimation (F16)
100% 573
0.69 IPS
 
Pose Estimation (I8)
100% 2691
3.26 IPS
 
Object Detection (F32)
100% 297
22.2 IPS
 
Object Detection (F16)
100% 299
22.3 IPS
 
Object Detection (I8)
61% 668
49.9 IPS
 
Face Detection (F32)
100% 582
6.92 IPS
 
Face Detection (F16)
100% 592
7.03 IPS
 
Face Detection (I8)
86% 1208
14.4 IPS
 
Depth Estimation (F32)
100% 598
4.63 IPS
 
Depth Estimation (F16)
100% 606
4.70 IPS
 
Depth Estimation (I8)
95% 1268
9.84 IPS
 
Style Transfer (F32)
100% 953
1.25 IPS
 
Style Transfer (F16)
100% 953
1.25 IPS
 
Style Transfer (I8)
98% 2450
3.22 IPS
 
Image Super-Resolution (F32)
100% 366
13.1 IPS
 
Image Super-Resolution (F16)
100% 361
12.9 IPS
 
Image Super-Resolution (I8)
98% 1510
53.9 IPS
 
Text Classification (F32)
100% 322
462.7 IPS
 
Text Classification (F16)
100% 354
509.2 IPS
 
Text Classification (I8)
92% 264
379.4 IPS
 
Machine Translation (F32)
100% 684
12.6 IPS
 
Machine Translation (F16)
100% 679
12.5 IPS
 
Machine Translation (I8)
64% 219
4.03 IPS
 

Compare

Set Baseline Geekbench 6 now available