Samsung Galaxy S20 Ultra 5G
Geekbench ML Score
419
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | October 06 2022 11:47 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 12 |
| Model | Samsung Galaxy S20 Ultra 5G |
| Model ID | samsung SM-G988U |
| 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 @ 2.84 GHz |
| Memory Information | |
|---|---|
| Size | 10.35 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
414
44.3 IPS |
|
|
Image Classification (F16)
|
100% |
293
31.4 IPS |
|
|
Image Classification (I8)
|
81% |
204
21.8 IPS |
|
|
Image Segmentation (F32)
|
100% |
634
3.92 IPS |
|
|
Image Segmentation (F16)
|
100% |
628
3.88 IPS |
|
|
Image Segmentation (I8)
|
89% |
903
5.58 IPS |
|
|
Pose Estimation (F32)
|
100% |
270
1.09 IPS |
|
|
Pose Estimation (F16)
|
100% |
248
1.00 IPS |
|
|
Pose Estimation (I8)
|
80% |
246
1.00 IPS |
|
|
Object Detection (F32)
|
100% |
399
14.0 IPS |
|
|
Object Detection (F16)
|
100% |
395
13.9 IPS |
|
|
Object Detection (I8)
|
52% |
284
9.97 IPS |
|
|
Face Detection (F32)
|
100% |
613
7.05 IPS |
|
|
Face Detection (F16)
|
100% |
641
7.37 IPS |
|
|
Face Detection (I8)
|
75% |
587
6.74 IPS |
|
|
Text Classification (F32)
|
100% |
356
140.7 IPS |
|
|
Text Classification (F16)
|
100% |
396
156.8 IPS |
|
|
Machine Translation (F32)
|
100% |
567
87.3 IPS |
|
|
Machine Translation (F16)
|
100% |
569
87.7 IPS |
