Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
1173
TensorFlow Lite NNAPI Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 24 2021 12:55 AM |
| Views | 2 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998U1 |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| 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 | NNAPI |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
1019
109.2 IPS |
|
|
Image Classification (F16)
|
100% |
1707
182.9 IPS |
|
|
Image Classification (I8)
|
79% |
4937
529.0 IPS |
|
|
Image Segmentation (F32)
|
100% |
2409
14.9 IPS |
|
|
Image Segmentation (F16)
|
71% |
3602
22.2 IPS |
|
|
Image Segmentation (I8)
|
89% |
10781
66.6 IPS |
|
|
Pose Estimation (F32)
|
100% |
569
2.30 IPS |
|
|
Pose Estimation (F16)
|
100% |
1992
8.06 IPS |
|
|
Pose Estimation (I8)
|
80% |
24807
100.4 IPS |
|
|
Object Detection (F32)
|
100% |
898
31.5 IPS |
|
|
Object Detection (F16)
|
100% |
1216
42.7 IPS |
|
|
Object Detection (I8)
|
56% |
1803
63.3 IPS |
|
|
Face Detection (F32)
|
100% |
624
7.17 IPS |
|
|
Face Detection (F16)
|
100% |
632
7.26 IPS |
|
|
Face Detection (I8)
|
76% |
22795
261.9 IPS |
|
|
Text Classification (F32)
|
100% |
10
4.08 IPS |
|
|
Text Classification (F16)
|
46% |
10
4.11 IPS |
|
|
Machine Translation (F32)
|
100% |
700
107.8 IPS |
|
|
Machine Translation (F16)
|
100% |
752
116.0 IPS |
