samsung SM-S928U
Geekbench ML Score
1323
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | August 28 2024 08:52 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | samsung SM-S928U |
| Model ID | samsung SM-S928U |
| 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 | GPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
862
161.4 IPS |
|
|
Image Classification (F16)
|
100% |
925
173.2 IPS |
|
|
Image Classification (I8)
|
99% |
655
122.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
825
13.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
1134
18.9 IPS |
|
|
Image Segmentation (I8)
|
98% |
1075
18.0 IPS |
|
|
Pose Estimation (F32)
|
100% |
1074
1.30 IPS |
|
|
Pose Estimation (F16)
|
100% |
2675
3.24 IPS |
|
|
Pose Estimation (I8)
|
100% |
2467
2.99 IPS |
|
|
Object Detection (F32)
|
100% |
286
21.4 IPS |
|
|
Object Detection (F16)
|
100% |
428
32.0 IPS |
|
|
Object Detection (I8)
|
62% |
451
33.6 IPS |
|
|
Face Detection (F32)
|
100% |
2613
31.1 IPS |
|
|
Face Detection (F16)
|
97% |
3146
37.4 IPS |
|
|
Face Detection (I8)
|
86% |
2854
33.9 IPS |
|
|
Depth Estimation (F32)
|
100% |
1778
13.8 IPS |
|
|
Depth Estimation (F16)
|
100% |
3894
30.2 IPS |
|
|
Depth Estimation (I8)
|
95% |
3756
29.1 IPS |
|
|
Style Transfer (F32)
|
100% |
6540
8.60 IPS |
|
|
Style Transfer (F16)
|
100% |
11106
14.6 IPS |
|
|
Style Transfer (I8)
|
98% |
11116
14.6 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
461
16.5 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
1363
48.7 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1291
46.1 IPS |
|
|
Text Classification (F32)
|
100% |
433
622.0 IPS |
|
|
Text Classification (F16)
|
100% |
431
619.1 IPS |
|
|
Text Classification (I8)
|
92% |
708
1.02 KIPS |
|
|
Machine Translation (F32)
|
100% |
717
13.2 IPS |
|
|
Machine Translation (F16)
|
100% |
703
12.9 IPS |
|
|
Machine Translation (I8)
|
64% |
811
14.9 IPS |
