Samsung Galaxy S22 Ultra
Geekbench ML Score
1133
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | January 21 2024 01:36 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% |
433
81.0 IPS |
|
|
Image Classification (F16)
|
100% |
456
85.2 IPS |
|
|
Image Classification (I8)
|
99% |
420
78.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
1206
20.1 IPS |
|
|
Image Segmentation (F16)
|
100% |
1501
25.1 IPS |
|
|
Image Segmentation (I8)
|
98% |
1417
23.7 IPS |
|
|
Pose Estimation (F32)
|
100% |
1891
2.29 IPS |
|
|
Pose Estimation (F16)
|
100% |
2532
3.07 IPS |
|
|
Pose Estimation (I8)
|
100% |
2730
3.31 IPS |
|
|
Object Detection (F32)
|
100% |
492
36.7 IPS |
|
|
Object Detection (F16)
|
100% |
347
25.9 IPS |
|
|
Object Detection (I8)
|
58% |
327
24.4 IPS |
|
|
Face Detection (F32)
|
100% |
1857
22.1 IPS |
|
|
Face Detection (F16)
|
97% |
1954
23.2 IPS |
|
|
Face Detection (I8)
|
86% |
1853
22.0 IPS |
|
|
Depth Estimation (F32)
|
100% |
2116
16.4 IPS |
|
|
Depth Estimation (F16)
|
100% |
2702
21.0 IPS |
|
|
Depth Estimation (I8)
|
95% |
2703
21.0 IPS |
|
|
Style Transfer (F32)
|
100% |
5960
7.84 IPS |
|
|
Style Transfer (F16)
|
100% |
8484
11.2 IPS |
|
|
Style Transfer (I8)
|
98% |
8597
11.3 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
1117
39.9 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
1417
50.6 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1430
51.1 IPS |
|
|
Text Classification (F32)
|
100% |
246
353.5 IPS |
|
|
Text Classification (F16)
|
100% |
245
352.2 IPS |
|
|
Text Classification (I8)
|
92% |
459
660.1 IPS |
|
|
Machine Translation (F32)
|
100% |
423
7.78 IPS |
|
|
Machine Translation (F16)
|
100% |
417
7.68 IPS |
|
|
Machine Translation (I8)
|
64% |
553
10.2 IPS |
