samsung SM-T978U
Geekbench ML Score
358
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | June 12 2021 08:27 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 | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
275
29.5 IPS |
|
|
Image Classification (F16)
|
100% |
265
28.4 IPS |
|
|
Image Classification (I8)
|
81% |
206
22.1 IPS |
|
|
Image Segmentation (F32)
|
100% |
533
3.29 IPS |
|
|
Image Segmentation (F16)
|
100% |
524
3.23 IPS |
|
|
Image Segmentation (I8)
|
89% |
705
4.36 IPS |
|
|
Pose Estimation (F32)
|
100% |
245
0.99 IPS |
|
|
Pose Estimation (F16)
|
100% |
243
0.98 IPS |
|
|
Pose Estimation (I8)
|
80% |
210
0.85 IPS |
|
|
Object Detection (F32)
|
100% |
334
11.7 IPS |
|
|
Object Detection (F16)
|
100% |
366
12.8 IPS |
|
|
Object Detection (I8)
|
52% |
261
9.17 IPS |
|
|
Face Detection (F32)
|
100% |
555
6.38 IPS |
|
|
Face Detection (F16)
|
100% |
547
6.28 IPS |
|
|
Face Detection (I8)
|
75% |
450
5.17 IPS |
|
|
Text Classification (F32)
|
100% |
335
132.4 IPS |
|
|
Text Classification (F16)
|
100% |
327
129.2 IPS |
|
|
Machine Translation (F32)
|
100% |
437
67.3 IPS |
|
|
Machine Translation (F16)
|
100% |
444
68.5 IPS |
