Samsung Galaxy S21 Ultra 5G
Geekbench ML Score
416
TensorFlow Lite CPU Inference Score
Geekbench ML 0.6.0 for Android AArch64
Result Information
| Upload Date | March 27 2024 07:22 PM |
| Views | 1 |
System Information
| System Information | |
|---|---|
| Operating System | Android 13 |
| Model | Samsung Galaxy S21 Ultra 5G |
| Model ID | samsung SM-G998B |
| Motherboard | exynos2100 |
| Governor | energy_step |
| CPU Information | |
|---|---|
| Name | ARM ARMv8 |
| Topology | 1 Processor, 8 Cores |
| Identifier | ARM implementer 65 architecture 8 variant 1 part 3396 revision 0 |
| Base Frequency | 2.21 GHz |
| Cluster 1 | 4 Cores @ 2.21 GHz |
| Cluster 2 | 3 Cores @ 2.81 GHz |
| Cluster 3 | 1 Core @ 2.91 GHz |
| Memory Information | |
|---|---|
| Size | 14.25 GB |
| Inference Information | |
|---|---|
| Framework | TensorFlow Lite |
| Backend | CPU |
| Device | Default |
Inference Performance
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (F32)
|
100% |
192
35.9 IPS |
|
|
Image Classification (F16)
|
100% |
186
34.8 IPS |
|
|
Image Classification (I8)
|
97% |
334
62.5 IPS |
|
|
Image Segmentation (F32)
|
100% |
336
5.62 IPS |
|
|
Image Segmentation (F16)
|
100% |
319
5.32 IPS |
|
|
Image Segmentation (I8)
|
98% |
478
7.98 IPS |
|
|
Pose Estimation (F32)
|
100% |
635
0.77 IPS |
|
|
Pose Estimation (F16)
|
100% |
522
0.63 IPS |
|
|
Pose Estimation (I8)
|
100% |
2279
2.76 IPS |
|
|
Object Detection (F32)
|
100% |
152
11.4 IPS |
|
|
Object Detection (F16)
|
100% |
162
12.1 IPS |
|
|
Object Detection (I8)
|
61% |
353
26.4 IPS |
|
|
Face Detection (F32)
|
100% |
372
4.43 IPS |
|
|
Face Detection (F16)
|
100% |
379
4.50 IPS |
|
|
Face Detection (I8)
|
86% |
798
9.49 IPS |
|
|
Depth Estimation (F32)
|
100% |
384
2.98 IPS |
|
|
Depth Estimation (F16)
|
100% |
400
3.10 IPS |
|
|
Depth Estimation (I8)
|
95% |
944
7.32 IPS |
|
|
Style Transfer (F32)
|
100% |
1004
1.32 IPS |
|
|
Style Transfer (F16)
|
100% |
995
1.31 IPS |
|
|
Style Transfer (I8)
|
98% |
2193
2.88 IPS |
|
|
Image Super-Resolution (F32)
|
100% |
290
10.3 IPS |
|
|
Image Super-Resolution (F16)
|
100% |
271
9.69 IPS |
|
|
Image Super-Resolution (I8)
|
98% |
955
34.1 IPS |
|
|
Text Classification (F32)
|
100% |
284
407.8 IPS |
|
|
Text Classification (F16)
|
100% |
264
379.8 IPS |
|
|
Text Classification (I8)
|
92% |
300
431.6 IPS |
|
|
Machine Translation (F32)
|
100% |
298
5.49 IPS |
|
|
Machine Translation (F16)
|
100% |
285
5.25 IPS |
|
|
Machine Translation (I8)
|
64% |
189
3.47 IPS |
