alps k65v1_64_bsp
Geekbench AI Score
36
Single Precision Score
50
Half Precision Score
49
Quantized Score
Geekbench AI 1.2.0 for Android AArch64
Result Information
| Upload Date | December 04 2024 12:22 PM |
| Views | 17 |
System Information
| AI Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | ARM ARMv8 |
| System Information | |
|---|---|
| Operating System | Android 15 |
| Model | alps k65v1_64_bsp |
| Model ID | alps k65v1_64_bsp |
| Motherboard | k65v1_64_bsp |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 0 part 3331 revision 4 |
| Base Frequency | 2.20 GHz |
| Cluster 1 | 4 Cores @ 1.60 GHz |
| Cluster 2 | 4 Cores @ 2.20 GHz |
| Memory Information | |
|---|---|
| Size | 5.70 GB |
AI Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
24
4.50 IPS |
|
|
Image Classification (HP)
|
100% |
36
6.61 IPS |
|
|
Image Classification (Q)
|
99% |
34
6.40 IPS |
|
|
Image Segmentation (SP)
|
100% |
37
0.61 IPS |
|
|
Image Segmentation (HP)
|
100% |
46
0.75 IPS |
|
|
Image Segmentation (Q)
|
98% |
46
0.75 IPS |
|
|
Pose Estimation (SP)
|
100% |
29
0.03 IPS |
|
|
Pose Estimation (HP)
|
100% |
51
0.06 IPS |
|
|
Pose Estimation (Q)
|
95% |
48
0.06 IPS |
|
|
Object Detection (SP)
|
100% |
18
1.40 IPS |
|
|
Object Detection (HP)
|
100% |
25
2.01 IPS |
|
|
Object Detection (Q)
|
85% |
24
1.95 IPS |
|
|
Face Detection (SP)
|
100% |
73
0.87 IPS |
|
|
Face Detection (HP)
|
100% |
97
1.16 IPS |
|
|
Face Detection (Q)
|
97% |
92
1.09 IPS |
|
|
Depth Estimation (SP)
|
100% |
47
0.36 IPS |
|
|
Depth Estimation (HP)
|
99% |
74
0.57 IPS |
|
|
Depth Estimation (Q)
|
63% |
59
0.55 IPS |
|
|
Style Transfer (SP)
|
100% |
95
0.12 IPS |
|
|
Style Transfer (HP)
|
100% |
160
0.21 IPS |
|
|
Style Transfer (Q)
|
98% |
151
0.20 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
21
0.77 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
35
1.29 IPS |
|
|
Image Super-Resolution (Q)
|
97% |
32
1.20 IPS |
|
|
Text Classification (SP)
|
100% |
28
37.8 IPS |
|
|
Text Classification (HP)
|
100% |
29
39.0 IPS |
|
|
Text Classification (Q)
|
91% |
47
62.7 IPS |
|
|
Machine Translation (SP)
|
100% |
49
0.84 IPS |
|
|
Machine Translation (HP)
|
100% |
48
0.83 IPS |
|
|
Machine Translation (Q)
|
57% |
42
1.02 IPS |
