Samsung Galaxy S20 Ultra
Geekbench ML Score
326
TensorFlow Lite CPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | June 13 2021 01:31 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S20 Ultra |
| Model ID | samsung SM-G988B |
| Motherboard | exynos990 |
| Governor | energy_step |
| CPU Information | |
|---|---|
| Name | ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 83 architecture 8 variant 1 part 4 revision 0 |
| Base Frequency | 2.00 GHz |
| Cluster 1 | 4 Cores @ 2.00 GHz |
| Cluster 2 | 2 Cores @ 2.50 GHz |
| Cluster 3 | 2 Cores @ 2.73 GHz |
| Memory Information | |
|---|---|
| Size | 10.65 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
165
17.7 IPS |
|
|
Image Classification (F16)
|
100% |
159
17.1 IPS |
|
|
Image Classification (I8)
|
81% |
181
19.4 IPS |
|
|
Image Segmentation (F32)
|
100% |
441
2.72 IPS |
|
|
Image Segmentation (F16)
|
100% |
440
2.72 IPS |
|
|
Image Segmentation (I8)
|
89% |
799
4.93 IPS |
|
|
Pose Estimation (F32)
|
100% |
250
1.01 IPS |
|
|
Pose Estimation (F16)
|
100% |
247
1.00 IPS |
|
|
Pose Estimation (I8)
|
80% |
228
0.92 IPS |
|
|
Object Detection (F32)
|
100% |
223
7.82 IPS |
|
|
Object Detection (F16)
|
100% |
226
7.94 IPS |
|
|
Object Detection (I8)
|
52% |
248
8.70 IPS |
|
|
Face Detection (F32)
|
100% |
351
4.03 IPS |
|
|
Face Detection (F16)
|
100% |
374
4.29 IPS |
|
|
Face Detection (I8)
|
75% |
475
5.46 IPS |
|
|
Text Classification (F32)
|
100% |
369
145.8 IPS |
|
|
Text Classification (F16)
|
100% |
358
141.5 IPS |
|
|
Machine Translation (F32)
|
100% |
742
114.3 IPS |
|
|
Machine Translation (F16)
|
100% |
746
115.0 IPS |
