Samsung Galaxy S20+
Geekbench ML Score
779
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | September 28 2021 11:42 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 11 |
| Model | Samsung Galaxy S20+ |
| Model ID | samsung SM-G986B |
| 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 | 10.64 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | GPU |
| Device | |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
466
49.9 IPS |
|
|
Image Classification (F16)
|
100% |
860
92.2 IPS |
|
|
Image Classification (I8)
|
80% |
808
86.6 IPS |
|
|
Image Segmentation (F32)
|
100% |
1065
6.58 IPS |
|
|
Image Segmentation (F16)
|
100% |
1983
12.2 IPS |
|
|
Image Segmentation (I8)
|
89% |
1982
12.2 IPS |
|
|
Pose Estimation (F32)
|
100% |
361
1.46 IPS |
|
|
Pose Estimation (F16)
|
100% |
1084
4.38 IPS |
|
|
Pose Estimation (I8)
|
80% |
1084
4.39 IPS |
|
|
Object Detection (F32)
|
100% |
355
12.5 IPS |
|
|
Object Detection (F16)
|
100% |
397
13.9 IPS |
|
|
Object Detection (I8)
|
54% |
420
14.7 IPS |
|
|
Face Detection (F32)
|
100% |
1074
12.3 IPS |
|
|
Face Detection (F16)
|
97% |
2174
25.0 IPS |
|
|
Face Detection (I8)
|
75% |
1979
22.7 IPS |
|
|
Text Classification (F32)
|
100% |
530
209.7 IPS |
|
|
Text Classification (F16)
|
98% |
722
285.7 IPS |
|
|
Machine Translation (F32)
|
100% |
383
59.0 IPS |
|
|
Machine Translation (F16)
|
100% |
382
58.9 IPS |
