Khadas rk3588_s
Geekbench ML Score
544
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 06 2022 05:30 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Khadas rk3588_s |
| Model ID | Khadas rk3588_s |
| Motherboard | rk30sdk |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 4 part 3339 revision 0 |
| Base Frequency | 1.80 GHz |
| Cluster 1 | 4 Cores @ 1.80 GHz |
| Cluster 2 | 2 Cores @ 2.26 GHz |
| Cluster 3 | 2 Cores @ 2.30 GHz |
| Memory Information | |
|---|---|
| Size | 7.49 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
395
42.3 IPS |
|
|
Image Classification (F16)
|
100% |
660
70.7 IPS |
|
|
Image Classification (I8)
|
81% |
583
62.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
875
5.40 IPS |
|
|
Image Segmentation (F16)
|
100% |
1330
8.22 IPS |
|
|
Image Segmentation (I8)
|
89% |
1352
8.35 IPS |
|
|
Pose Estimation (F32)
|
100% |
284
1.15 IPS |
|
|
Pose Estimation (F16)
|
100% |
722
2.92 IPS |
|
|
Pose Estimation (I8)
|
80% |
723
2.93 IPS |
|
|
Object Detection (F32)
|
100% |
279
9.81 IPS |
|
|
Object Detection (F16)
|
99% |
382
13.4 IPS |
|
|
Object Detection (I8)
|
54% |
383
13.4 IPS |
|
|
Face Detection (F32)
|
100% |
392
4.50 IPS |
|
|
Face Detection (F16)
|
97% |
1389
16.0 IPS |
|
|
Face Detection (I8)
|
75% |
1211
13.9 IPS |
|
|
Text Classification (F32)
|
100% |
524
207.1 IPS |
|
|
Text Classification (F16)
|
98% |
808
319.6 IPS |
|
|
Machine Translation (F32)
|
100% |
154
23.8 IPS |
|
|
Machine Translation (F16)
|
100% |
154
23.7 IPS |
