Samsung Galaxy S22 Ultra
Geekbench ML Score
1116
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | July 05 2024 08:56 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Samsung Galaxy S22 Ultra |
| Model ID | samsung SM-S908B |
| Motherboard | s5e9925 |
| Governor | energy_aware |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 2 part 3400 revision 0 |
| Base Frequency | 1.82 GHz |
| Cluster 1 | 4 Cores @ 1.82 GHz |
| Cluster 2 | 3 Cores @ 2.52 GHz |
| Cluster 3 | 1 Core @ 2.80 GHz |
| Memory Information | |
|---|---|
| Size | 7.12 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
397
74.3 IPS |
|
|
Image Classification (F16)
|
100% |
465
87.0 IPS |
|
|
Image Classification (I8)
|
99% |
368
68.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
1207
20.2 IPS |
|
|
Image Segmentation (F16)
|
100% |
1499
25.0 IPS |
|
|
Image Segmentation (I8)
|
98% |
1462
24.4 IPS |
|
|
Pose Estimation (F32)
|
100% |
1911
2.31 IPS |
|
|
Pose Estimation (F16)
|
100% |
2567
3.11 IPS |
|
|
Pose Estimation (I8)
|
100% |
2759
3.34 IPS |
|
|
Object Detection (F32)
|
100% |
419
31.3 IPS |
|
|
Object Detection (F16)
|
100% |
336
25.1 IPS |
|
|
Object Detection (I8)
|
58% |
330
24.7 IPS |
|
|
Face Detection (F32)
|
100% |
1872
22.3 IPS |
|
|
Face Detection (F16)
|
97% |
1905
22.6 IPS |
|
|
Face Detection (I8)
|
86% |
1837
21.8 IPS |
|
|
Depth Estimation (F32)
|
100% |
2130
16.5 IPS |
|
|
Depth Estimation (F16)
|
100% |
2730
21.2 IPS |
|
|
Depth Estimation (I8)
|
95% |
2733
21.2 IPS |
|
|
Style Transfer (F32)
|
100% |
6059
7.97 IPS |
|
|
Style Transfer (F16)
|
100% |
8664
11.4 IPS |
|
|
Style Transfer (I8)
|
98% |
8795
11.6 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
1063
38.0 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
1320
47.1 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1367
48.8 IPS |
|
|
Text Classification (F32)
|
100% |
244
350.7 IPS |
|
|
Text Classification (F16)
|
100% |
245
351.6 IPS |
|
|
Text Classification (I8)
|
92% |
460
660.7 IPS |
|
|
Machine Translation (F32)
|
100% |
422
7.76 IPS |
|
|
Machine Translation (F16)
|
100% |
416
7.65 IPS |
|
|
Machine Translation (I8)
|
64% |
540
9.95 IPS |
