Samsung Galaxy S22 Ultra
Geekbench ML Score
1167
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | September 04 2024 08:07 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% |
425
79.5 IPS |
|
|
Image Classification (F16)
|
100% |
492
92.1 IPS |
|
|
Image Classification (I8)
|
99% |
532
99.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
1205
20.1 IPS |
|
|
Image Segmentation (F16)
|
100% |
1480
24.7 IPS |
|
|
Image Segmentation (I8)
|
98% |
1440
24.1 IPS |
|
|
Pose Estimation (F32)
|
100% |
1889
2.29 IPS |
|
|
Pose Estimation (F16)
|
100% |
2536
3.07 IPS |
|
|
Pose Estimation (I8)
|
100% |
2729
3.30 IPS |
|
|
Object Detection (F32)
|
100% |
504
37.6 IPS |
|
|
Object Detection (F16)
|
100% |
542
40.5 IPS |
|
|
Object Detection (I8)
|
58% |
479
35.8 IPS |
|
|
Face Detection (F32)
|
100% |
2098
24.9 IPS |
|
|
Face Detection (F16)
|
97% |
2316
27.5 IPS |
|
|
Face Detection (I8)
|
86% |
2127
25.3 IPS |
|
|
Depth Estimation (F32)
|
100% |
2196
17.0 IPS |
|
|
Depth Estimation (F16)
|
100% |
2740
21.2 IPS |
|
|
Depth Estimation (I8)
|
95% |
2780
21.6 IPS |
|
|
Style Transfer (F32)
|
100% |
5957
7.84 IPS |
|
|
Style Transfer (F16)
|
100% |
8508
11.2 IPS |
|
|
Style Transfer (I8)
|
98% |
8632
11.4 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
952
34.0 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
1227
43.8 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1144
40.9 IPS |
|
|
Text Classification (F32)
|
100% |
237
341.1 IPS |
|
|
Text Classification (F16)
|
100% |
238
341.6 IPS |
|
|
Text Classification (I8)
|
92% |
456
655.5 IPS |
|
|
Machine Translation (F32)
|
100% |
406
7.47 IPS |
|
|
Machine Translation (F16)
|
100% |
395
7.26 IPS |
|
|
Machine Translation (I8)
|
64% |
516
9.49 IPS |
