Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
596
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | January 21 2024 09:35 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998U |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM SM8350 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 3 Cores @ 2.42 GHz |
| Cluster 3 | 1 Core @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 10.07 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
284
53.1 IPS |
|
|
Image Classification (F16)
|
100% |
270
50.5 IPS |
|
|
Image Classification (I8)
|
97% |
652
121.9 IPS |
|
|
Image Segmentation (F32)
|
100% |
352
5.88 IPS |
|
|
Image Segmentation (F16)
|
100% |
362
6.04 IPS |
|
|
Image Segmentation (I8)
|
98% |
535
8.94 IPS |
|
|
Pose Estimation (F32)
|
100% |
551
0.67 IPS |
|
|
Pose Estimation (F16)
|
100% |
551
0.67 IPS |
|
|
Pose Estimation (I8)
|
100% |
2703
3.27 IPS |
|
|
Object Detection (F32)
|
100% |
285
21.2 IPS |
|
|
Object Detection (F16)
|
100% |
281
21.0 IPS |
|
|
Object Detection (I8)
|
61% |
807
60.3 IPS |
|
|
Face Detection (F32)
|
100% |
644
7.66 IPS |
|
|
Face Detection (F16)
|
100% |
600
7.14 IPS |
|
|
Face Detection (I8)
|
86% |
1452
17.3 IPS |
|
|
Depth Estimation (F32)
|
100% |
580
4.50 IPS |
|
|
Depth Estimation (F16)
|
100% |
594
4.61 IPS |
|
|
Depth Estimation (I8)
|
95% |
1544
12.0 IPS |
|
|
Style Transfer (F32)
|
100% |
1142
1.50 IPS |
|
|
Style Transfer (F16)
|
100% |
1114
1.47 IPS |
|
|
Style Transfer (I8)
|
98% |
2800
3.68 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
394
14.1 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
378
13.5 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1304
46.6 IPS |
|
|
Text Classification (F32)
|
100% |
365
524.0 IPS |
|
|
Text Classification (F16)
|
100% |
356
512.1 IPS |
|
|
Text Classification (I8)
|
92% |
289
415.2 IPS |
|
|
Machine Translation (F32)
|
100% |
662
12.2 IPS |
|
|
Machine Translation (F16)
|
100% |
649
12.0 IPS |
|
|
Machine Translation (I8)
|
64% |
311
5.71 IPS |
