samsung SM-T978U
Geekbench ML Score
1313
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | June 12 2021 08:29 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | samsung SM-T978U |
| Model ID | samsung SM-T978U |
| Motherboard | kona |
| Governor | schedutil |
| CPU Information | |
|---|---|
| Name | ARM Qualcomm |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3341 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 @ 3.09 GHz |
| Memory Information | |
|---|---|
| Size | 5.43 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
956
102.4 IPS |
|
|
Image Classification (F16)
|
100% |
1596
171.0 IPS |
|
|
Image Classification (I8)
|
80% |
1422
152.3 IPS |
|
|
Image Segmentation (F32)
|
100% |
2560
15.8 IPS |
|
|
Image Segmentation (F16)
|
100% |
4244
26.2 IPS |
|
|
Image Segmentation (I8)
|
89% |
3946
24.4 IPS |
|
|
Pose Estimation (F32)
|
100% |
1320
5.34 IPS |
|
|
Pose Estimation (F16)
|
100% |
2275
9.21 IPS |
|
|
Pose Estimation (I8)
|
80% |
2256
9.13 IPS |
|
|
Object Detection (F32)
|
100% |
555
19.5 IPS |
|
|
Object Detection (F16)
|
99% |
767
26.9 IPS |
|
|
Object Detection (I8)
|
53% |
748
26.3 IPS |
|
|
Face Detection (F32)
|
100% |
1897
21.8 IPS |
|
|
Face Detection (F16)
|
97% |
3078
35.4 IPS |
|
|
Face Detection (I8)
|
76% |
2758
31.7 IPS |
|
|
Text Classification (F32)
|
100% |
503
198.9 IPS |
|
|
Text Classification (F16)
|
98% |
570
225.4 IPS |
|
|
Machine Translation (F32)
|
100% |
444
68.5 IPS |
|
|
Machine Translation (F16)
|
100% |
435
67.1 IPS |
