UNISOC ums9620_2h10_native
Geekbench AI Score
107
Single Precision Score
107
Half Precision Score
771
Quantized Score
Geekbench AI 1.1.0 for Android AArch64
Result Information
| Upload Date | November 08 2024 08:25 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 | 2.00 GHz |
| Cluster 1 | 4 Cores @ 2.00 GHz |
| Cluster 2 | 4 Cores @ 2.21 GHz |
| Memory Information | |
|---|---|
| Size | 5.26 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
64
12.0 IPS |
|
|
Image Classification (HP)
|
100% |
64
11.8 IPS |
|
|
Image Classification (Q)
|
99% |
636
118.6 IPS |
|
|
Image Segmentation (SP)
|
100% |
90
1.46 IPS |
|
|
Image Segmentation (HP)
|
100% |
90
1.46 IPS |
|
|
Image Segmentation (Q)
|
98% |
572
9.30 IPS |
|
|
Pose Estimation (SP)
|
100% |
111
0.13 IPS |
|
|
Pose Estimation (HP)
|
100% |
110
0.13 IPS |
|
|
Pose Estimation (Q)
|
96% |
14337
16.8 IPS |
|
|
Object Detection (SP)
|
100% |
63
4.96 IPS |
|
|
Object Detection (HP)
|
100% |
64
5.06 IPS |
|
|
Object Detection (Q)
|
84% |
553
44.6 IPS |
|
|
Face Detection (SP)
|
100% |
180
2.14 IPS |
|
|
Face Detection (HP)
|
100% |
182
2.16 IPS |
|
|
Face Detection (Q)
|
97% |
2116
25.2 IPS |
|
|
Depth Estimation (SP)
|
100% |
137
1.05 IPS |
|
|
Depth Estimation (HP)
|
99% |
137
1.06 IPS |
|
|
Depth Estimation (Q)
|
63% |
702
6.56 IPS |
|
|
Style Transfer (SP)
|
100% |
251
0.32 IPS |
|
|
Style Transfer (HP)
|
100% |
251
0.32 IPS |
|
|
Style Transfer (Q)
|
87% |
3471
4.52 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
65
2.39 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
65
2.40 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
1684
62.4 IPS |
|
|
Text Classification (SP)
|
100% |
86
114.9 IPS |
|
|
Text Classification (HP)
|
100% |
86
114.2 IPS |
|
|
Text Classification (Q)
|
91% |
30
40.2 IPS |
|
|
Machine Translation (SP)
|
100% |
149
2.57 IPS |
|
|
Machine Translation (HP)
|
100% |
150
2.59 IPS |
|
|
Machine Translation (Q)
|
57% |
100
2.44 IPS |
