Samsung Galaxy S22 Ultra
Geekbench ML Score
1025
TensorFlow Lite GPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | August 30 2024 10:53 PM |
| Views | 2 |
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 | 10.27 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
344
64.4 IPS |
|
|
Image Classification (F16)
|
100% |
389
72.8 IPS |
|
|
Image Classification (I8)
|
99% |
357
66.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
507
8.47 IPS |
|
|
Image Segmentation (F16)
|
100% |
625
10.4 IPS |
|
|
Image Segmentation (I8)
|
98% |
607
10.1 IPS |
|
|
Pose Estimation (F32)
|
100% |
1906
2.31 IPS |
|
|
Pose Estimation (F16)
|
100% |
2563
3.10 IPS |
|
|
Pose Estimation (I8)
|
100% |
2752
3.33 IPS |
|
|
Object Detection (F32)
|
100% |
518
38.7 IPS |
|
|
Object Detection (F16)
|
100% |
313
23.4 IPS |
|
|
Object Detection (I8)
|
58% |
297
22.1 IPS |
|
|
Face Detection (F32)
|
100% |
1804
21.5 IPS |
|
|
Face Detection (F16)
|
97% |
2012
23.9 IPS |
|
|
Face Detection (I8)
|
86% |
1871
22.3 IPS |
|
|
Depth Estimation (F32)
|
100% |
2129
16.5 IPS |
|
|
Depth Estimation (F16)
|
100% |
2706
21.0 IPS |
|
|
Depth Estimation (I8)
|
95% |
2682
20.8 IPS |
|
|
Style Transfer (F32)
|
100% |
5933
7.80 IPS |
|
|
Style Transfer (F16)
|
100% |
8654
11.4 IPS |
|
|
Style Transfer (I8)
|
98% |
8799
11.6 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
1136
40.6 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
1541
55.0 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
1559
55.7 IPS |
|
|
Text Classification (F32)
|
100% |
246
354.1 IPS |
|
|
Text Classification (F16)
|
100% |
246
353.8 IPS |
|
|
Text Classification (I8)
|
92% |
460
660.7 IPS |
|
|
Machine Translation (F32)
|
100% |
427
7.85 IPS |
|
|
Machine Translation (F16)
|
100% |
426
7.85 IPS |
|
|
Machine Translation (I8)
|
64% |
549
10.1 IPS |
