UNISOC ums9620_2h10_native
Geekbench AI Score
134
Single Precision Score
134
Half Precision Score
879
Quantized Score
Geekbench AI 1.1.0 for Android AArch64
Result Information
| Upload Date | November 08 2024 08:14 AM |
| Views | 1 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | NNAPI |
| Device | ARM ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 15 |
| Model | UNISOC ums9620_2h10_native |
| Model ID | UNISOC ums9620_2h10_native |
| Motherboard | ums9620_2h10 |
| Governor | uscfreq |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
| Base Frequency | 2.18 GHz |
| Cluster 1 | 4 Cores @ 2.18 GHz |
| Cluster 2 | 3 Cores @ 2.30 GHz |
| Cluster 3 | 1 Core @ 2.70 GHz |
| Memory Information | |
|---|---|
| Size | 7.22 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
81
15.1 IPS |
|
|
Image Classification (HP)
|
100% |
81
15.1 IPS |
|
|
Image Classification (Q)
|
99% |
799
149.0 IPS |
|
|
Image Segmentation (SP)
|
100% |
111
1.80 IPS |
|
|
Image Segmentation (HP)
|
100% |
112
1.82 IPS |
|
|
Image Segmentation (Q)
|
98% |
604
9.82 IPS |
|
|
Pose Estimation (SP)
|
100% |
138
0.16 IPS |
|
|
Pose Estimation (HP)
|
100% |
138
0.16 IPS |
|
|
Pose Estimation (Q)
|
96% |
23774
27.8 IPS |
|
|
Object Detection (SP)
|
100% |
80
6.31 IPS |
|
|
Object Detection (HP)
|
100% |
80
6.35 IPS |
|
|
Object Detection (Q)
|
84% |
564
45.5 IPS |
|
|
Face Detection (SP)
|
100% |
219
2.60 IPS |
|
|
Face Detection (HP)
|
100% |
221
2.63 IPS |
|
|
Face Detection (Q)
|
97% |
1967
23.5 IPS |
|
|
Depth Estimation (SP)
|
100% |
168
1.29 IPS |
|
|
Depth Estimation (HP)
|
99% |
169
1.30 IPS |
|
|
Depth Estimation (Q)
|
63% |
839
7.85 IPS |
|
|
Style Transfer (SP)
|
100% |
303
0.39 IPS |
|
|
Style Transfer (HP)
|
100% |
303
0.39 IPS |
|
|
Style Transfer (Q)
|
87% |
4128
5.37 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
81
2.99 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
81
2.98 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1537
57.0 IPS |
|
|
Text Classification (SP)
|
100% |
115
153.0 IPS |
|
|
Text Classification (HP)
|
100% |
115
153.4 IPS |
|
|
Text Classification (Q)
|
91% |
33
44.5 IPS |
|
|
Machine Translation (SP)
|
100% |
187
3.22 IPS |
|
|
Machine Translation (HP)
|
100% |
190
3.27 IPS |
|
|
Machine Translation (Q)
|
57% |
124
3.03 IPS |
