Samsung Galaxy Note20 Ultra
Geekbench ML Score
754
TensorFlow Lite GPU Inference Score
Geekbench ML 0.5.0 for Android AArch64
Result Information
| Upload Date | August 13 2023 07:56 AM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Samsung Galaxy Note20 Ultra |
| Model ID | samsung SM-N986B |
| 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% |
478
51.2 IPS |
|
|
Image Classification (F16)
|
100% |
835
89.4 IPS |
|
|
Image Classification (I8)
|
80% |
798
85.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
1110
6.86 IPS |
|
|
Image Segmentation (F16)
|
100% |
1935
12.0 IPS |
|
|
Image Segmentation (I8)
|
89% |
1964
12.1 IPS |
|
|
Pose Estimation (F32)
|
100% |
390
1.58 IPS |
|
|
Pose Estimation (F16)
|
100% |
1109
4.49 IPS |
|
|
Pose Estimation (I8)
|
80% |
1106
4.47 IPS |
|
|
Object Detection (F32)
|
100% |
284
9.98 IPS |
|
|
Object Detection (F16)
|
100% |
424
14.9 IPS |
|
|
Object Detection (I8)
|
54% |
405
14.2 IPS |
|
|
Face Detection (F32)
|
100% |
1131
13.0 IPS |
|
|
Face Detection (F16)
|
97% |
2249
25.8 IPS |
|
|
Face Detection (I8)
|
75% |
2062
23.7 IPS |
|
|
Text Classification (F32)
|
100% |
571
225.7 IPS |
|
|
Text Classification (F16)
|
98% |
557
220.2 IPS |
|
|
Machine Translation (F32)
|
100% |
301
46.3 IPS |
|
|
Machine Translation (F16)
|
100% |
299
46.1 IPS |
