samsung SM-S928B
Geekbench ML Score
1304
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | August 20 2024 01:48 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | samsung SM-S928B |
| Model ID | samsung SM-S928B |
| Motherboard | pineapple |
| Governor | walt |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3458 revision 1 |
| Base Frequency | 2.26 GHz |
| Cluster 1 | 2 Cores @ 2.27 GHz |
| Cluster 2 | 2 Cores @ 2.96 GHz |
| Cluster 3 | 3 Cores @ 3.15 GHz |
| Cluster 4 | 1 Core @ 3.40 GHz |
| Memory Information | |
|---|---|
| Size | 10.81 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
623
116.5 IPS |
|
|
Image Classification (F16)
|
100% |
615
115.0 IPS |
|
|
Image Classification (I8)
|
97% |
1074
201.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
835
13.9 IPS |
|
|
Image Segmentation (F16)
|
100% |
835
13.9 IPS |
|
|
Image Segmentation (I8)
|
98% |
967
16.2 IPS |
|
|
Pose Estimation (F32)
|
100% |
1495
1.81 IPS |
|
|
Pose Estimation (F16)
|
100% |
1461
1.77 IPS |
|
|
Pose Estimation (I8)
|
100% |
6311
7.64 IPS |
|
|
Object Detection (F32)
|
100% |
626
46.7 IPS |
|
|
Object Detection (F16)
|
100% |
633
47.3 IPS |
|
|
Object Detection (I8)
|
61% |
1402
104.7 IPS |
|
|
Face Detection (F32)
|
100% |
1493
17.8 IPS |
|
|
Face Detection (F16)
|
100% |
1478
17.6 IPS |
|
|
Face Detection (I8)
|
86% |
2514
29.9 IPS |
|
|
Depth Estimation (F32)
|
100% |
1403
10.9 IPS |
|
|
Depth Estimation (F16)
|
100% |
1399
10.8 IPS |
|
|
Depth Estimation (I8)
|
95% |
2744
21.3 IPS |
|
|
Style Transfer (F32)
|
100% |
2502
3.29 IPS |
|
|
Style Transfer (F16)
|
100% |
2450
3.22 IPS |
|
|
Style Transfer (I8)
|
98% |
5423
7.13 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
1032
36.9 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
989
35.3 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
2877
102.8 IPS |
|
|
Text Classification (F32)
|
100% |
779
1.12 KIPS |
|
|
Text Classification (F16)
|
100% |
747
1.07 KIPS |
|
|
Text Classification (I8)
|
92% |
618
888.6 IPS |
|
|
Machine Translation (F32)
|
100% |
1471
27.1 IPS |
|
|
Machine Translation (F16)
|
100% |
1478
27.2 IPS |
|
|
Machine Translation (I8)
|
64% |
597
11.0 IPS |
