Samsung Galaxy S21 Ultra 5G
Geekbench AI Score
675
Single Precision Score
601
Half Precision Score
1031
Quantized Score
Geekbench AI 1.2.0 for Android AArch64
Result Information
| Upload Date | December 29 2024 02:46 AM |
| Views | 3 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Qualcomm Snapdragon 888 |
| System Information | |
|---|---|
| Operating System | Android 14 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998U1 |
| Motherboard | lahaina |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM SM8350 |
| 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 |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
375
69.8 IPS |
|
|
Image Classification (HP)
|
100% |
375
69.8 IPS |
|
|
Image Classification (Q)
|
100% |
999
185.7 IPS |
|
|
Image Segmentation (SP)
|
100% |
478
7.75 IPS |
|
|
Image Segmentation (HP)
|
100% |
478
7.75 IPS |
|
|
Image Segmentation (Q)
|
98% |
1177
19.1 IPS |
|
|
Pose Estimation (SP)
|
100% |
1897
2.21 IPS |
|
|
Pose Estimation (HP)
|
100% |
1842
2.15 IPS |
|
|
Pose Estimation (Q)
|
84% |
2289
2.71 IPS |
|
|
Object Detection (SP)
|
100% |
337
26.8 IPS |
|
|
Object Detection (HP)
|
100% |
330
26.2 IPS |
|
|
Object Detection (Q)
|
83% |
947
76.5 IPS |
|
|
Face Detection (SP)
|
100% |
1199
14.2 IPS |
|
|
Face Detection (HP)
|
100% |
1200
14.3 IPS |
|
|
Face Detection (Q)
|
95% |
2271
27.1 IPS |
|
|
Depth Estimation (SP)
|
100% |
1567
12.1 IPS |
|
|
Depth Estimation (HP)
|
99% |
1556
12.0 IPS |
|
|
Depth Estimation (Q)
|
64% |
1711
15.7 IPS |
|
|
Style Transfer (SP)
|
89% |
2731
3.54 IPS |
|
|
Style Transfer (HP)
|
89% |
2805
3.64 IPS |
|
|
Style Transfer (Q)
|
98% |
5374
6.93 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
843
31.1 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
281
10.4 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
632
23.4 IPS |
|
|
Text Classification (SP)
|
100% |
163
217.7 IPS |
|
|
Text Classification (HP)
|
100% |
162
216.7 IPS |
|
|
Text Classification (Q)
|
88% |
266
359.1 IPS |
|
|
Machine Translation (SP)
|
100% |
244
4.20 IPS |
|
|
Machine Translation (HP)
|
100% |
240
4.14 IPS |
|
|
Machine Translation (Q)
|
50% |
153
5.42 IPS |
